Most Influential NIPS Papers (2023-09)

September 25, 2023September 29, 2023 admin

The Conference on Neural Information Processing Systems (NIPS) is one of the top machine learning conferences in the world. Paper Digest Team analyzes all papers published on NIPS in the past years, and presents the 15 most influential papers for each year. This ranking list is automatically constructed based upon citations from both research papers and granted patents, and will be frequently updated to reflect the most recent changes. To find the latest version of this list or the most influential papers from other conferences/journals, please visit Best Paper Digest page. Note: the most influential papers may or may not include the papers that won the best paper awards. (Version: 2023-09)

To search or review papers within NIPS related to a specific topic, please use the search by venue (NIPS) and review by venue (NIPS) services. To browse the most productive NIPS authors by year ranked by #papers accepted, here is a list of most productive NIPS authors.

Based in New York, Paper Digest is dedicated to producing high-quality text analysis results that people can acturally use on a daily basis. Since 2018, we have been serving users across the world with a number of exclusive services to track, search, review and rewrite scientific literature.

You are welcome to follow us on Twitter and Linkedin to get updated with new conference digests.

Paper Digest Team
New York City, New York, 10017
team@paperdigest.org

TABLE 1: Most Influential NIPS Papers (2023-09)

Year	Rank	Paper	Author(s)
2022	1	Training Language Models to Follow Instructions with Human Feedback IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We fine-tune GPT-3 using data collected from human labelers. The resulting model, called InstructGPT, outperforms GPT-3 on a range of NLP tasks.	LONG OUYANG et. al.
2022	2	Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present Imagen, a text-to-image diffusion model with an unprecedented degree of photorealism and a deep level of language understanding.	CHITWAN SAHARIA et. al.
2022	3	Chain of Thought Prompting Elicits Reasoning in Large Language Models IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We explore how generating a chain of thought—a series of intermediate reasoning steps—significantly improves the ability of large language models to perform complex reasoning.	JASON WEI et. al.
2022	4	Flamingo: A Visual Language Model for Few-Shot Learning IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Building models that can be rapidly adapted to novel tasks using only a handful of annotated examples is an open challenge for multimodal machine learning research. We introduce Flamingo, a family of Visual Language Models (VLM) with this ability.	JEAN-BAPTISTE ALAYRAC et. al.
2022	5	Large Language Models Are Zero-Shot Reasoners IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a single zero-shot prompt that elicits effective chain of thought reasoning across diverse benchmarks that require multi-step thinking.	Takeshi Kojima; Shixiang (Shane) Gu; Machel Reid; Yutaka Matsuo; Yusuke Iwasawa;
2022	6	LAION-5B: An Open Large-scale Dataset for Training Next Generation Image-text Models IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present LAION-5B, an open, publically available dataset of 5.8B image-text pairs and validate it by reproducing results of training state-of-the-art CLIP models of different scale.	CHRISTOPH SCHUHMANN et. al.
2022	7	The Surprising Effectiveness of PPO in Cooperative Multi-Agent Games IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We demonstrate PPO’s effectiveness in popular multi-agent benchmarks and analyze its properties and implementation details through empirical studies.	CHAO YU et. al.
2022	8	Video Diffusion Models IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To generate long and higher resolution videos we introduce a new conditional sampling technique for spatial and temporal video extension that performs better than previously proposed methods.	JONATHAN HO et. al.
2022	9	Elucidating The Design Space of Diffusion-Based Generative Models IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We argue that the theory and practice of diffusion-based generative models are currently unnecessarily convoluted and seek to remedy the situation by presenting a design space that clearly separates the concrete design choices.	Tero Karras; Miika Aittala; Timo Aila; Samuli Laine;
2022	10	VideoMAE: Masked Autoencoders Are Data-Efficient Learners for Self-Supervised Video Pre-Training IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we show that video masked autoencoders (VideoMAE) are data-efficient learners for self-supervised video pre-training (SSVP).	Zhan Tong; Yibing Song; Jue Wang; Limin Wang;
2022	11	DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose an exact formulation of the solution of diffusion ODEs.	CHENG LU et. al.
2022	12	Diffusion-LM Improves Controllable Text Generation IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: While recent works have demonstrated successes on controlling simple sentence attributes (e.g., sentiment), there has been little progress on complex, fine-grained controls (e.g., syntactic structure). To address this challenge, we develop a new non-autoregressive language model based on continuous diffusions that we call Diffusion-LM.	Xiang Li; John Thickstun; Ishaan Gulrajani; Percy Liang; Tatsunori Hashimoto;
2022	13	Solving Quantitative Reasoning Problems with Language Models IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We train a large Transformer language model on mathematical data and achieve strong performance on quantitative reasoning tasks, including state of the art performance on the MATH dataset.	AITOR LEWKOWYCZ et. al.
2022	14	Denoising Diffusion Restoration Models IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This work addresses these issues by introducing Denoising Diffusion Restoration Models (DDRM), an efficient, unsupervised posterior sampling method.	Bahjat Kawar; Michael Elad; Stefano Ermon; Jiaming Song;
2022	15	FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a fast and memory-efficient exact attention algorithm by accounting for GPU memory reads/writes, yielding faster end-to-end training time and higher quality models with longer sequences.	Tri Dao; Dan Fu; Stefano Ermon; Atri Rudra; Christopher Ré;
2021	1	Diffusion Models Beat GANs on Image Synthesis IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We show that diffusion models can achieve image sample quality superior to the current state-of-the-art generative models.	Prafulla Dhariwal; Alexander Nichol;
2021	2	SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present SegFormer, a simple, efficient yet powerful semantic segmentation framework which unifies Transformers with lightweight multilayer perceptron (MLP) decoders.	ENZE XIE et. al.
2021	3	MLP-Mixer: An All-MLP Architecture for Vision IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we show that while convolutions and attention are both sufficient for good performance, neither of them are necessary.	ILYA O. TOLSTIKHIN et. al.
2021	4	Alias-Free Generative Adversarial Networks IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Interpreting all signals in the network as continuous, we derive generally applicable, small architectural changes that guarantee that unwanted information cannot leak into the hierarchical synthesis process.	TERO KARRAS et. al.
2021	5	Transformer in Transformer IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we point out that the attention inside these local patches are also essential for building visual transformers with high performance and we explore a new architecture, namely, Transformer iN Transformer (TNT).	KAI HAN et. al.
2021	6	Align Before Fuse: Vision and Language Representation Learning with Momentum Distillation IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we introduce a contrastive loss to ALign the image and text representations BEfore Fusing (ALBEF) them through cross-modal attention, which enables more grounded vision and language representation learning.	JUNNAN LI et. al.
2021	7	Decision Transformer: Reinforcement Learning Via Sequence Modeling IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce a framework that abstracts Reinforcement Learning (RL) as a sequence modeling problem.	LILI CHEN et. al.
2021	8	CoAtNet: Marrying Convolution and Attention for All Data Sizes IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we show that while Transformers tend to have larger model capacity, their generalization can be worse than convolutional networks due to the lack of the right inductive bias.	Zihang Dai; Hanxiao Liu; Quoc Le; Mingxing Tan;
2021	9	Per-Pixel Classification Is Not All You Need for Semantic Segmentation IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Following this observation, we propose MaskFormer, a simple mask classification model which predicts a set of binary masks, each associated with a single global class label prediction.	Bowen Cheng; Alex Schwing; Alexander Kirillov;
2021	10	Twins: Revisiting The Design of Spatial Attention in Vision Transformers IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we revisit the design of the spatial attention and demonstrate that a carefully devised yet simple spatial attention mechanism performs favorably against the state-of-the-art schemes.	XIANGXIANG CHU et. al.
2021	11	NeuS: Learning Neural Implicit Surfaces By Volume Rendering for Multi-view Reconstruction IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a novel neural surface reconstruction method, called NeuS, for reconstructing objects and scenes with high fidelity from 2D image inputs.	PENG WANG et. al.
2021	12	Do Vision Transformers See Like Convolutional Neural Networks? IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Analyzing the internal representation structure of ViTs and CNNs on image classification benchmarks, we find striking differences between the two architectures, such as ViT having more uniform representations across all layers.	Maithra Raghu; Thomas Unterthiner; Simon Kornblith; Chiyuan Zhang; Alexey Dosovitskiy;
2021	13	Provably Efficient Reinforcement Learning with Linear Function Approximation Under Adaptivity Constraints IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We consider two popular limited adaptivity models: the batch learning model and the rare policy switch model, and propose two efficient online RL algorithms for episodic linear Markov decision processes, where the transition probability and the reward function can be represented as a linear function of some known feature mapping.	Tianhao Wang; Dongruo Zhou; Quanquan Gu;
2021	14	Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper studies the long-term forecasting problem of time series.	haixu wu; Jiehui Xu; Jianmin Wang; Mingsheng Long;
2021	15	Early Convolutions Help Transformers See Better IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In particular, they are sensitive to the choice of optimizer (AdamW vs. SGD), optimizer hyperparameters, and training schedule length. In comparison, modern convolutional neural networks are easier to optimize. Why is this the case? In this work, we conjecture that the issue lies with the patchify stem of ViT models, which is implemented by a stride-p p×p convolution (p = 16 by default) applied to the input image.	TETE XIAO et. al.
2020	1	Language Models Are Few-Shot Learners IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Specifically, we train GPT-3, an autoregressive language model with 175 billion parameters, 10x more than any previous non-sparse language model, and test its performance in the few-shot setting.	TOM BROWN et. al.
2020	2	Denoising Diffusion Probabilistic Models IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present high quality image synthesis results using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics.	Jonathan Ho; Ajay Jain; Pieter Abbeel;
2020	3	Wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We show for the first time that learning powerful representations from speech audio alone followed by fine-tuning on transcribed speech can outperform the best semi-supervised methods while being conceptually simpler.	Alexei Baevski; Yuhao Zhou; Abdel-rahman Mohamed; Michael Auli;
2020	4	Supervised Contrastive Learning IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we extend the self-supervised batch contrastive approach to the fully-supervised setting, allowing us to effectively leverage label information.	PRANNAY KHOSLA et. al.
2020	5	Unsupervised Learning of Visual Features By Contrasting Cluster Assignments IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose an online algorithm, SwAV, that takes advantage of contrastive methods without requiring to compute pairwise comparisons.	MATHILDE CARON et. al.
2020	6	RandAugment: Practical Automated Data Augmentation with A Reduced Search Space IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we rethink the process of designing automated data augmentation strategies.	Ekin Dogus Cubuk; Barret Zoph; Jon Shlens; Quoc Le;
2020	7	FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we propose FixMatch, an algorithm that is a significant simplification of existing SSL methods.	KIHYUK SOHN et. al.
2020	8	Decision-Making with Auto-Encoding Variational Bayes IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Motivated by these theoretical results, we propose learning several approximate proposals for the best model and combining them using multiple importance sampling for decision-making.	Romain Lopez; Pierre Boyeau; Nir Yosef; Michael Jordan; Jeffrey Regier;
2020	9	Unsupervised Data Augmentation for Consistency Training IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we present a new perspective on how to effectively noise unlabeled examples and argue that the quality of noising, specifically those produced by advanced data augmentation methods, plays a crucial role in semi-supervised learning.	Qizhe Xie; Zihang Dai; Eduard Hovy; Thang Luong; Quoc Le;
2020	10	Big Self-Supervised Models Are Strong Semi-Supervised Learners IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A key ingredient of our approach is the use of big (deep and wide) networks during pretraining and fine-tuning. We find that, the fewer the labels, the more this approach (task-agnostic use of unlabeled data) benefits from a bigger network.	Ting Chen; Simon Kornblith; Kevin Swersky; Mohammad Norouzi; Geoffrey E. Hinton;
2020	11	Open Graph Benchmark: Datasets for Machine Learning on Graphs IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present the Open Graph Benchmark (OGB), a diverse set of challenging and realistic benchmark datasets to facilitate scalable, robust, and reproducible graph machine learning (ML) research.	WEIHUA HU et. al.
2020	12	Implicit Neural Representations with Periodic Activation Functions IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose to leverage periodic activation functions for implicit neural representations and demonstrate that these networks, dubbed sinusoidal representation networks or SIRENs, are ideally suited for representing complex natural signals and their derivatives.	Vincent Sitzmann; Julien Martel; Alexander Bergman; David Lindell; Gordon Wetzstein;
2020	13	Big Bird: Transformers for Longer Sequences IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To remedy this, we propose, BigBird, a sparse attention mechanism that reduces this quadratic dependency to linear.	MANZIL ZAHEER et. al.
2020	14	Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We suggest an approach for selecting problem-specific Fourier features that greatly improves the performance of MLPs for low-dimensional regression tasks relevant to the computer vision and graphics communities.	MATTHEW TANCIK et. al.
2020	15	Training Generative Adversarial Networks with Limited Data IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose an adaptive discriminator augmentation mechanism that significantly stabilizes training in limited data regimes.	TERO KARRAS et. al.
2019	1	PyTorch: An Imperative Style, High-Performance Deep Learning Library IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we detail the principles that drove the implementation of PyTorch and how they are reflected in its architecture.	ADAM PASZKE et. al.
2019	2	XLNet: Generalized Autoregressive Pretraining for Language Understanding IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In light of these pros and cons, we propose XLNet, a generalized autoregressive pretraining method that (1) enables learning bidirectional contexts by maximizing the expected likelihood over all permutations of the factorization order and (2) overcomes the limitations of BERT thanks to its autoregressive formulation.	ZHILIN YANG et. al.
2019	3	ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present ViLBERT (short for Vision-and-Language BERT), a model for learning task-agnostic joint representations of image content and natural language.	Jiasen Lu; Dhruv Batra; Devi Parikh; Stefan Lee;
2019	4	Cross-lingual Language Model Pretraining IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we extend this approach to multiple languages and show the effectiveness of cross-lingual pretraining.	Alexis CONNEAU; Guillaume Lample;
2019	5	MixMatch: A Holistic Approach to Semi-Supervised Learning IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we unify the current dominant approaches for semi-supervised learning to produce a new algorithm, MixMatch, that guesses low-entropy labels for data-augmented unlabeled examples and mixes labeled and unlabeled data using MixUp.	DAVID BERTHELOT et. al.
2019	6	Generative Modeling By Estimating Gradients of The Data Distribution IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce a new generative model where samples are produced via Langevin dynamics using gradients of the data distribution estimated with score matching.	Yang Song; Stefano Ermon;
2019	7	SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we present SuperGLUE, a new benchmark styled after GLUE with a new set of more difficult language understanding tasks, a software toolkit, and a public leaderboard.	ALEX WANG et. al.
2019	8	Adversarial Examples Are Not Bugs, They Are Features IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We demonstrate that adversarial examples can be directly attributed to the presence of non-robust features: features (derived from patterns in the data distribution) that are highly predictive, yet brittle and (thus) incomprehensible to humans.	ANDREW ILYAS et. al.
2019	9	When Does Label Smoothing Help? IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We show that label smoothing encourages the representations of training examples from the same class to group in tight clusters.	Rafael M�ller; Simon Kornblith; Geoffrey E. Hinton;
2019	10	Unified Language Model Pre-training for Natural Language Understanding and Generation IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a new Unified pre-trained Language Model (UniLM) that can be fine-tuned for both natural language understanding and generation tasks.	LI DONG et. al.
2019	11	Deep Leakage from Gradients IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, in this paper, we show that we can obtain the private training set from the publicly shared gradients.	Ligeng Zhu; Zhijian Liu; Song Han;
2019	12	Learning Representations By Maximizing Mutual Information Across Views IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose an approach to self-supervised representation learning based on maximizing mutual information between features extracted from multiple views of a shared context.	Philip Bachman; R Devon Hjelm; William Buchwalter;
2019	13	Generating Diverse High-Fidelity Images with VQ-VAE-2 IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We explore the use of Vector Quantized Variational AutoEncoder (VQ-VAE) models for large scale image generation.	Ali Razavi; Aaron van den Oord; Oriol Vinyals;
2019	14	GPipe: Efficient Training of Giant Neural Networks Using Pipeline Parallelism IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To address the need for efficient and task-independent model parallelism, we introduce TensorPipe, a pipeline parallelism library that allows scaling any network that can be expressed as a sequence of layers.	YANPING HUANG et. al.
2019	15	Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Deep learning algorithms can fare poorly when the training dataset suffers from heavy class-imbalance but the testing criterion requires good generalization on less frequent classes. We design two novel methods to improve performance in such scenarios.	Kaidi Cao; Colin Wei; Adrien Gaidon; Nikos Arechiga; Tengyu Ma;
2018	1	Neural Ordinary Differential Equations IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce a new family of deep neural network models.	Tian Qi Chen; Yulia Rubanova; Jesse Bettencourt; David K. Duvenaud;
2018	2	Glow: Generative Flow with Invertible 1×1 Convolutions IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we propose Glow, a simple type of generative flow using invertible 1×1 convolution.	Durk P. Kingma; Prafulla Dhariwal;
2018	3	PointCNN: Convolution On X-Transformed Points IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a simple and general framework for feature learning from point cloud.	YANGYAN LI et. al.
2018	4	Neural Tangent Kernel: Convergence and Generalization in Neural Networks IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We prove that the evolution of an ANN during training can also be described by a kernel: during gradient descent on the parameters of an ANN, the network function (which maps input vectors to output vectors) follows the so-called kernel gradient associated with a new object, which we call the Neural Tangent Kernel (NTK).	Arthur Jacot; Franck Gabriel; Clement Hongler;
2018	5	Hierarchical Graph Representation Learning with Differentiable Pooling IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here we propose DiffPool, a differentiable graph pooling module that can generate hierarchical representations of graphs and can be combined with various graph neural network architectures in an end-to-end fashion.	ZHITAO YING et. al.
2018	6	Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we present a theoretically grounded set of noise-robust loss functions that can be seen as a generalization of MAE and CCE.	Zhilu Zhang; Mert Sabuncu;
2018	7	Conditional Adversarial Domain Adaptation IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present conditional adversarial domain adaptation, a principled framework that conditions the adversarial adaptation models on discriminative information conveyed in the classifier predictions.	Mingsheng Long; ZHANGJIE CAO; Jianmin Wang; Michael I. Jordan;
2018	8	Sanity Checks for Saliency Maps IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose an actionable methodology to evaluate what kinds of explanations a given method can and cannot provide.	JULIUS ADEBAYO et. al.
2018	9	Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Therefore in this paper, we propose a new deep learning paradigm called ”Co-teaching” for combating with noisy labels.	BO HAN et. al.
2018	10	Visualizing The Loss Landscape of Neural Nets IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we explore the structure of neural loss functions, and the effect of loss landscapes on generalization, using a range of visualization methods.	Hao Li; Zheng Xu; Gavin Taylor; Christoph Studer; Tom Goldstein;
2018	11	A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a simple yet effective method for detecting any abnormal samples, which is applicable to any pre-trained softmax neural classifier.	Kimin Lee; Kibok Lee; Honglak Lee; Jinwoo Shin;
2018	12	Link Prediction Based on Graph Neural Networks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we study this heuristic learning paradigm for link prediction.	Muhan Zhang; Yixin Chen;
2018	13	How Does Batch Normalization Help Optimization? IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we demonstrate that such distributional stability of layer inputs has little to do with the success of BatchNorm.	Shibani Santurkar; Dimitris Tsipras; Andrew Ilyas; Aleksander Madry;
2018	14	TADAM: Task Dependent Adaptive Metric for Improved Few-shot Learning IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we identify that metric scaling and metric task conditioning are important to improve the performance of few-shot algorithms.	Boris Oreshkin; Pau Rodr�guez L�pez; Alexandre Lacoste;
2018	15	Deep Reinforcement Learning in A Handful of Trials Using Probabilistic Dynamics Models IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we study how to bridge this gap, by employing uncertainty-aware dynamics models.	Kurtland Chua; Roberto Calandra; Rowan McAllister; Sergey Levine;
2017	1	Attention Is All You Need IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a novel, simple network architecture based solely onan attention mechanism, dispensing with recurrence and convolutions entirely.Experiments on two machine translation tasks show these models to be superiorin quality while being more parallelizable and requiring significantly less timeto train.	ASHISH VASWANI et. al.
2017	2	A Unified Approach to Interpreting Model Predictions IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To address this problem, we present a unified framework for interpreting predictions, SHAP (SHapley Additive exPlanations).	Scott M. Lundberg; Su-In Lee;
2017	3	Inductive Representation Learning on Large Graphs IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here we present GraphSAGE, a general, inductive framework that leverages node feature information (e.g., text attributes) to efficiently generate node embeddings.	Will Hamilton; Zhitao Ying; Jure Leskovec;
2017	4	GANs Trained By A Two Time-Scale Update Rule Converge to A Local Nash Equilibrium IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a two time-scale update rule (TTUR) for training GANs with stochastic gradient descent on arbitrary GAN loss functions.	Martin Heusel; Hubert Ramsauer; Thomas Unterthiner; Bernhard Nessler; Sepp Hochreiter;
2017	5	Improved Training of Wasserstein GANs IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose an alternative to clipping weights: penalize the norm of gradient of the critic with respect to its input.	Ishaan Gulrajani; Faruk Ahmed; Martin Arjovsky; Vincent Dumoulin; Aaron C. Courville;
2017	6	PointNet++: Deep Hierarchical Feature Learning on Point Sets in A Metric Space IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we introduce a hierarchical neural network that applies PointNet recursively on a nested partitioning of the input point set. With further observation that point sets are usually sampled with varying densities, which results in greatly decreased performance for networks trained on uniform densities, we propose novel set learning layers to adaptively combine features from multiple scales.	Charles Ruizhongtai Qi; Li Yi; Hao Su; Leonidas J. Guibas;
2017	7	LightGBM: A Highly Efficient Gradient Boosting Decision Tree IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To tackle this problem, we propose two novel techniques: \emph{Gradient-based One-Side Sampling} (GOSS) and \emph{Exclusive Feature Bundling} (EFB).	GUOLIN KE et. al.
2017	8	Prototypical Networks for Few-shot Learning IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose Prototypical Networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each new class.	Jake Snell; Kevin Swersky; Richard Zemel;
2017	9	Simple and Scalable Predictive Uncertainty Estimation Using Deep Ensembles IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose an alternative to Bayesian NNs that is simple to implement, readily parallelizable, requires very little hyperparameter tuning, and yields high quality predictive uncertainty estimates.	Balaji Lakshminarayanan; Alexander Pritzel; Charles Blundell;
2017	10	Dynamic Routing Between Capsules IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We use the length of the activity vector to represent the probability that the entity exists and its orientation to represent the instantiation parameters.	Sara Sabour; Nicholas Frosst; Geoffrey E. Hinton;
2017	11	What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: For this we present a Bayesian deep learning framework combining input-dependent aleatoric uncertainty together with epistemic uncertainty.	Alex Kendall; Yarin Gal;
2017	12	Mean Teachers Are Better Role Models: Weight-averaged Consistency Targets Improve Semi-supervised Deep Learning Results IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To overcome this problem, we propose Mean Teacher, a method that averages model weights instead of label predictions.	Antti Tarvainen; Harri Valpola;
2017	13	Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We explore deep reinforcement learning methods for multi-agent domains.	RYAN LOWE et. al.
2017	14	Neural Discrete Representation Learning IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a simple yet powerful generative model that learns such discrete representations.	Aaron van den Oord; Oriol Vinyals; koray kavukcuoglu;
2017	15	Unsupervised Image-to-Image Translation Networks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To address the problem, we make a shared-latent space assumption and propose an unsupervised image-to-image translation framework based on Coupled GANs.	Ming-Yu Liu; Thomas Breuel; Jan Kautz;
2016	1	Improved Techniques for Training GANs IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a variety of new architectural features and training procedures that we apply to the generative adversarial networks (GANs) framework.	TIM SALIMANS et. al.
2016	2	Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we are interested in generalizing convolutional neural networks (CNNs) from low-dimensional regular grids, where image, video and speech are represented, to high-dimensional irregular domains, such as social networks, brain connectomes or words’ embedding, represented by graphs.	Micha�l Defferrard; Xavier Bresson; Pierre Vandergheynst;
2016	3	Matching Networks for One Shot Learning IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we employ ideas from metric learning based on deep neural features and from recent advances that augment neural networks with external memories.	Oriol Vinyals; Charles Blundell; Timothy Lillicrap; koray kavukcuoglu; Daan Wierstra;
2016	4	R-FCN: Object Detection Via Region-based Fully Convolutional Networks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present region-based, fully convolutional networks for accurate and efficient object detection.	Jifeng Dai; Yi Li; Kaiming He; Jian Sun;
2016	5	InfoGAN: Interpretable Representation Learning By Information Maximizing Generative Adversarial Nets IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper describes InfoGAN, an information-theoretic extension to the Generative Adversarial Network that is able to learn disentangled representations in a completely unsupervised manner.	XI CHEN et. al.
2016	6	Equality of Opportunity in Supervised Learning IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a criterion for discrimination against a specified sensitive attribute in supervised learning, where the goal is to predict some target based on available features.	Moritz Hardt; Eric Price; Nati Srebro;
2016	7	Man Is to Computer Programmer As Woman Is to Homemaker? Debiasing Word Embeddings IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This raises concerns because their widespread use, as we describe, often tends to amplify these biases.	Tolga Bolukbasi; Kai-Wei Chang; James Y. Zou; Venkatesh Saligrama; Adam T. Kalai;
2016	8	Generative Adversarial Imitation Learning IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a new general framework for directly extracting a policy from data as if it were obtained by reinforcement learning following inverse reinforcement learning.	Jonathan Ho; Stefano Ermon;
2016	9	Conditional Image Generation with PixelCNN Decoders IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This work explores conditional image generation with a new image density model based on the PixelCNN architecture.	AARON VAN DEN OORD et. al.
2016	10	Binarized Neural Networks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce a method to train Binarized Neural Networks (BNNs) – neural networks with binary weights and activations at run-time.	Itay Hubara; Matthieu Courbariaux; Daniel Soudry; Ran El-Yaniv; Yoshua Bengio;
2016	11	Learning Structured Sparsity in Deep Neural Networks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose a Structured Sparsity Learning (SSL) method to regularize the structures (i.e., filters, channels, filter shapes, and layer depth) of DNNs.	Wei Wen; Chunpeng Wu; Yandan Wang; Yiran Chen; Hai Li;
2016	12	Learning to Learn By Gradient Descent By Gradient Descent IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we show how the design of an optimization algorithm can be cast as a learning problem, allowing the algorithm to learn to exploit structure in the problems of interest in an automatic way.	MARCIN ANDRYCHOWICZ et. al.
2016	13	Learning A Probabilistic Latent Space of Object Shapes Via 3D Generative-Adversarial Modeling IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a novel framework, namely 3D Generative Adversarial Network (3D-GAN), which generates 3D objects from a probabilistic space by leveraging recent advances in volumetric convolutional networks and generative adversarial nets.	Jiajun Wu; Chengkai Zhang; Tianfan Xue; Bill Freeman; Josh Tenenbaum;
2016	14	Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present weight normalization: a reparameterization of the weight vectors in a neural network that decouples the length of those weight vectors from their direction.	Tim Salimans; Durk P. Kingma;
2016	15	Improved Deep Metric Learning with Multi-class N-pair Loss Objective IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose to address this problem with a new metric learning objective called multi-class N-pair loss.	Kihyuk Sohn;
2015	1	Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals.	Shaoqing Ren; Kaiming He; Ross Girshick; Jian Sun;
2015	2	Spatial Transformer Networks IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work we introduce a new learnable module, theSpatial Transformer, which explicitly allows the spatial manipulation ofdata within the network.	Max Jaderberg; Karen Simonyan; Andrew Zisserman; koray kavukcuoglu;
2015	3	Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we formulate precipitation nowcasting as a spatiotemporal sequence forecasting problem in which both the input and the prediction target are spatiotemporal sequences.	XINGJIAN SHI et. al.
2015	4	Learning Both Weights and Connections for Efficient Neural Network IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To address these limitations, we describe a method to reduce the storage and computation required by neural networks by an order of magnitude without affecting their accuracy by learning only the important connections.	Song Han; Jeff Pool; John Tran; William Dally;
2015	5	Character-level Convolutional Networks for Text Classification IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This article offers an empirical exploration on the use of character-level convolutional networks (ConvNets) for text classification. We constructed several large-scale datasets to show that character-level convolutional networks could achieve state-of-the-art or competitive results.	Xiang Zhang; Junbo Zhao; Yann LeCun;
2015	6	Teaching Machines to Read and Comprehend IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work we define a new methodology that resolves this bottleneck and provides large scale supervised reading comprehension data.	KARL MORITZ HERMANN et. al.
2015	7	Convolutional Networks on Graphs for Learning Molecular Fingerprints IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce a convolutional neural network that operates directly on graphs.These networks allow end-to-end learning of prediction pipelines whose inputs are graphs of arbitrary size and shape.The architecture we present generalizes standard molecular feature extraction methods based on circular fingerprints.We show that these data-driven features are more interpretable, and have better predictive performance on a variety of tasks.	DAVID K. DUVENAUD et. al.
2015	8	BinaryConnect: Training Deep Neural Networks with Binary Weights During Propagations IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce BinaryConnect, a method which consists in training a DNN with binary weights during the forward and backward propagations, while retaining precision of the stored weights in which gradients are accumulated.	Matthieu Courbariaux; Yoshua Bengio; Jean-Pierre David;
2015	9	End-To-End Memory Networks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce a neural network with a recurrent attention model over a possibly large external memory.	Sainbayar Sukhbaatar; arthur szlam; Jason Weston; Rob Fergus;
2015	10	Pointer Networks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce a new neural architecture to learn the conditional probability of an output sequence with elements that arediscrete tokens corresponding to positions in an input sequence.Such problems cannot be trivially addressed by existent approaches such as sequence-to-sequence and Neural Turing Machines,because the number of target classes in eachstep of the output depends on the length of the input, which is variable.Problems such as sorting variable sized sequences, and various combinatorialoptimization problems belong to this class.	Oriol Vinyals; Meire Fortunato; Navdeep Jaitly;
2015	11	Attention-Based Models for Speech Recognition IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We offer a qualitative explanation of this failure and propose a novel and generic method of adding location-awareness to the attention mechanism to alleviate this issue.	Jan K. Chorowski; Dzmitry Bahdanau; Dmitriy Serdyuk; Kyunghyun Cho; Yoshua Bengio;
2015	12	Learning Structured Output Representation Using Deep Conditional Generative Models IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we develop a scalable deep conditional generative model for structured output variables using Gaussian latent variables.	Kihyuk Sohn; Honglak Lee; Xinchen Yan;
2015	13	Skip-Thought Vectors IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We describe an approach for unsupervised learning of a generic, distributed sentence encoder.	RYAN KIROS et. al.
2015	14	Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a curriculum learning strategy to gently change the training process from a fully guided scheme using the true previous token, towards a less guided scheme which mostly uses the generated token instead.	Samy Bengio; Oriol Vinyals; Navdeep Jaitly; Noam Shazeer;
2015	15	Training Very Deep Networks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here we introduce a new architecture designed to overcome this.	Rupesh K. Srivastava; Klaus Greff; J�rgen Schmidhuber;
2014	1	Sequence to Sequence Learning with Neural Networks IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present a general end-to-end approach to sequence learning that makes minimal assumptions on the sequence structure.	Ilya Sutskever; Oriol Vinyals; Quoc V. Le;
2014	2	How Transferable Are Features in Deep Neural Networks? IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we experimentally quantify the generality versus specificity of neurons in each layer of a deep convolutional neural network and report a few surprising results.	Jason Yosinski; Jeff Clune; Yoshua Bengio; Hod Lipson;
2014	3	Two-Stream Convolutional Networks for Action Recognition in Videos IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Our contribution is three-fold.	Karen Simonyan; Andrew Zisserman;
2014	4	Depth Map Prediction from A Single Image Using A Multi-Scale Deep Network IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present a new method that addresses this task by employing two deep network stacks: one that makes a coarse global prediction based on the entire image, and another that refines this prediction locally.	David Eigen; Christian Puhrsch; Rob Fergus;
2014	5	Recurrent Models of Visual Attention IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a novel recurrent neural network model that is capable of extracting information from an image or video by adaptively selecting a sequence of regions or locations and only processing the selected regions at high resolution.	Volodymyr Mnih; Nicolas Heess; Alex Graves; koray kavukcuoglu;
2014	6	Learning Deep Features for Scene Recognition Using Places Database IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose new methods to compare the density and diversity of image datasets and show that Places is as dense as other scene datasets and has more diversity. Here, we introduce a new scene-centric database called Places with over 7 million labeled pictures of scenes.	Bolei Zhou; Agata Lapedriza; Jianxiong Xiao; Antonio Torralba; Aude Oliva;
2014	7	Semi-supervised Learning with Deep Generative Models IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We revisit the approach to semi-supervised learning with generative models and develop new models that allow for effective generalisation from small labelled data sets to large unlabelled ones.	Durk P. Kingma; Shakir Mohamed; Danilo Jimenez Rezende; Max Welling;
2014	8	Deep Learning Face Representation By Joint Identification-Verification IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we show that it can be well solved with deep learning and using both face identification and verification signals as supervision.	Yi Sun; Yuheng Chen; Xiaogang Wang; Xiaoou Tang;
2014	9	Do Deep Nets Really Need to Be Deep? IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we empirically demonstrate that shallow feed-forward nets can learn the complex functions previously learned by deep nets and achieve accuracies previously only achievable with deep models.	Jimmy Ba; Rich Caruana;
2014	10	Neural Word Embedding As Implicit Matrix Factorization IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We analyze skip-gram with negative-sampling (SGNS), a word embedding method introduced by Mikolov et al., and show that it is implicitly factorizing a word-context matrix, whose cells are the pointwise mutual information (PMI) of the respective word and context pairs, shifted by a global constant.	Omer Levy; Yoav Goldberg;
2014	11	SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work we introduce a new fast incremental gradient method SAGA, in the spirit of SAG, SDCA, MISO and SVRG.	Aaron Defazio; Francis Bach; Simon Lacoste-Julien;
2014	12	Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present techniques for speeding up the test-time evaluation of large convolutional networks, designed for object recognition tasks.	Emily L. Denton; Wojciech Zaremba; Joan Bruna; Yann LeCun; Rob Fergus;
2014	13	Joint Training of A Convolutional Network and A Graphical Model for Human Pose Estimation IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper proposes a new hybrid architecture that consists of a deep Convolutional Network and a Markov Random Field.	Jonathan J. Tompson; Arjun Jain; Yann LeCun; Christoph Bregler;
2014	14	Convolutional Neural Network Architectures for Matching Natural Language Sentences IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: As a step toward this goal, we propose convolutional neural network models for matching two sentences, by adapting the convolutional strategy in vision and speech.	Baotian Hu; Zhengdong Lu; Hang Li; Qingcai Chen;
2014	15	Identifying and Attacking The Saddle Point Problem in High-dimensional Non-convex Optimization IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Motivated by these arguments, we propose a new approach to second-order optimization, the saddle-free Newton method, that can rapidly escape high dimensional saddle points, unlike gradient descent and quasi-Newton methods.	YANN N. DAUPHIN et. al.
2013	1	Distributed Representations of Words and Phrases and Their Compositionality IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we present several improvements that make the Skip-gram model more expressive and enable it to learn higher quality vectors more rapidly.	Tomas Mikolov; Ilya Sutskever; Kai Chen; Greg S. Corrado; Jeff Dean;
2013	2	Translating Embeddings for Modeling Multi-relational Data IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Our objective is to propose a canonical model which is easy to train, contains a reduced number of parameters and can scale up to very large databases.	Antoine Bordes; Nicolas Usunier; Alberto Garcia-Duran; Jason Weston; Oksana Yakhnenko;
2013	3	Sinkhorn Distances: Lightspeed Computation of Optimal Transport IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose in this work a new family of optimal transportation distances that look at transportation problems from a maximum-entropy perspective.	Marco Cuturi;
2013	4	DeViSE: A Deep Visual-Semantic Embedding Model IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we present a new deep visual-semantic embedding model trained to identify visual objects using both labeled image data as well as semantic information gleaned from unannotated text.	ANDREA FROME et. al.
2013	5	Accelerating Stochastic Gradient Descent Using Predictive Variance Reduction IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To remedy this problem, we introduce an explicit variance reduction method for stochastic gradient descent which we call stochastic variance reduced gradient (SVRG).	Rie Johnson; Tong Zhang;
2013	6	Reasoning With Neural Tensor Networks for Knowledge Base Completion IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The goal of this paper is to develop a more powerful neural network model suitable for inference over these relationships.	Richard Socher; Danqi Chen; Christopher D. Manning; Andrew Ng;
2013	7	Deep Neural Networks for Object Detection IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we go one step further and address the problem of object detection — not only classifying but also precisely localizing objects of various classes using DNNs.	Christian Szegedy; Alexander Toshev; Dumitru Erhan;
2013	8	Zero-Shot Learning Through Cross-Modal Transfer IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This work introduces a model that can recognize objects in images even if no training data is available for the object class.	Richard Socher; Milind Ganjoo; Christopher D. Manning; Andrew Ng;
2013	9	Predicting Parameters in Deep Learning IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We demonstrate that there is significant redundancy in the parameterization of several deep learning models.	Misha Denil; Babak Shakibi; Laurent Dinh; Marc’Aurelio Ranzato; Nando de Freitas;
2013	10	Deep Content-based Music Recommendation IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose to use a latent factor model for recommendation, and predict the latent factors from music audio when they cannot be obtained from usage data.	Aaron van den Oord; Sander Dieleman; Benjamin Schrauwen;
2013	11	Learning with Noisy Labels IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we theoretically study the problem of binary classification in the presence of random classification noise — the learner, instead of seeing the true labels, sees labels that have independently been flipped with some small probability.	Nagarajan Natarajan; Inderjit S. Dhillon; Pradeep K. Ravikumar; Ambuj Tewari;
2013	12	Learning A Deep Compact Image Representation for Visual Tracking IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we study the challenging problem of tracking the trajectory of a moving object in a video with possibly very complex background.	Naiyan Wang; Dit-Yan Yeung;
2013	13	Understanding Variable Importances in Forests of Randomized Trees IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work we characterize the Mean Decrease Impurity (MDI) variable importances as measured by an ensemble of totally randomized trees in asymptotic sample and ensemble size conditions.	Gilles Louppe; Louis Wehenkel; Antonio Sutera; Pierre Geurts;
2013	14	More Effective Distributed ML Via A Stale Synchronous Parallel Parameter Server IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a parameter server system for distributed ML, which follows a Stale Synchronous Parallel (SSP) model of computation that maximizes the time computational workers spend doing useful work on ML algorithms, while still providing correctness guarantees.	QIRONG HO et. al.
2013	15	Multi-Task Bayesian Optimization IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we explore whether it is possible to transfer the knowledge gained from previous optimizations to new tasks in order to find optimal hyperparameter settings more efficiently.	Kevin Swersky; Jasper Snoek; Ryan P. Adams;
2012	1	ImageNet Classification with Deep Convolutional Neural Networks IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To reduce overfitting in the globally connected layers we employed a new regularization method that proved to be very effective.	Alex Krizhevsky; Ilya Sutskever; Geoffrey E. Hinton;
2012	2	Practical Bayesian Optimization of Machine Learning Algorithms IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we consider this problem through the framework of Bayesian optimization, in which a learning algorithm’s generalization performance is modeled as a sample from a Gaussian process (GP).	Jasper Snoek; Hugo Larochelle; Ryan P. Adams;
2012	3	Large Scale Distributed Deep Networks IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we consider the problem of training a deep network with billions of parameters using tens of thousands of CPU cores.	JEFFREY DEAN et. al.
2012	4	Multimodal Learning with Deep Boltzmann Machines IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a Deep Boltzmann Machine for learning a generative model of multimodal data.	Nitish Srivastava; Russ R. Salakhutdinov;
2012	5	Learning to Discover Social Circles in Ego Networks IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We pose the problem as a node clustering problem on a user’s ego-network, a network of connections between her friends. Experiments show that our model accurately identifies circles on a diverse set of data from Facebook, Google+, and Twitter for all of which we obtain hand-labeled ground-truth data.	Jure Leskovec; Julian J. Mcauley;
2012	6	Deep Neural Networks Segment Neuronal Membranes in Electron Microscopy Images IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We address a central problem of neuroanatomy, namely, the automatic segmentation of neuronal structures depicted in stacks of electron microscopy (EM) images.	Dan Ciresan; Alessandro Giusti; Luca M. Gambardella; J�rgen Schmidhuber;
2012	7	Image Denoising and Inpainting with Deep Neural Networks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a novel approach to low-level vision problems that combines sparse coding and deep networks pre-trained with denoising auto-encoder (DA).	Junyuan Xie; Linli Xu; Enhong Chen;
2012	8	Convolutional-Recursive Deep Learning for 3D Object Classification IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Richard Socher; Brody Huval; Bharath Bath; Christopher D. Manning; Andrew Y. Ng;
2012	9	Hamming Distance Metric Learning IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Motivated by large-scale multimedia applications we propose to learn mappings from high-dimensional data to binary codes that preserve semantic similarity.	Mohammad Norouzi; David J. Fleet; Russ R. Salakhutdinov;
2012	10	Optimal Kernel Choice for Large-scale Two-sample Tests IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Given samples from distributions $p$ and $q$, a two-sample test determines whether to reject the null hypothesis that $p=q$, based on the value of a test statistic measuring the …	ARTHUR GRETTON et. al.
2012	11	Communication-Efficient Algorithms for Statistical Optimization IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We study two communication-efficient algorithms for distributed statistical optimization on large-scale data.	Yuchen Zhang; Martin J. Wainwright; John C. Duchi;
2012	12	A Simple and Practical Algorithm for Differentially Private Data Release IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a new algorithm for differentially private data release, based on a simple combination of the Exponential Mechanism with the Multiplicative Weights update rule.	Moritz Hardt; Katrina Ligett; Frank Mcsherry;
2012	13	A Latent Factor Model for Highly Multi-relational Data IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a method for modeling large multi-relational datasets, with possibly thousands of relations.	Rodolphe Jenatton; Nicolas L. Roux; Antoine Bordes; Guillaume R. Obozinski;
2012	14	Learning from The Wisdom of Crowds By Minimax Entropy IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a minimax entropy principle to improve the quality of these labels.	Dengyong Zhou; Sumit Basu; Yi Mao; John C. Platt;
2012	15	Variational Inference for Crowdsourcing IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We approach this problem by transforming it into a standard inference problem in graphical models, and applying approximate variational methods, including belief propagation (BP) and mean field (MF).	Qiang Liu; Jian Peng; Alexander T. Ihler;
2011	1	Algorithms for Hyper-Parameter Optimization IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present hyper-parameter optimization results on tasks of training neural networks and deep belief networks (DBNs).	James S. Bergstra; R�mi Bardenet; Yoshua Bengio; Bal�zs K�gl;
2011	2	Hogwild: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This work aims to show using novel theoretical analysis, algorithms, and implementation that SGD can be implemented without any locking.	Benjamin Recht; Christopher Re; Stephen Wright; Feng Niu;
2011	3	Improved Algorithms for Linear Stochastic Bandits IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We improve the theoretical analysis and empirical performance of algorithms for the stochastic multi-armed bandit problem and the linear stochastic multi-armed bandit problem.	Yasin Abbasi-yadkori; D�vid P�l; Csaba Szepesv�ri;
2011	4	Practical Variational Inference for Neural Networks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper introduces an easy-to-implement stochastic variational method (or equivalently, minimum description length loss function) that can be applied to most neural networks.	Alex Graves;
2011	5	An Empirical Evaluation of Thompson Sampling IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present here some empirical results using Thompson sampling on simulated and real data, and show that it is highly competitive.	Olivier Chapelle; Lihong Li;
2011	6	Linearized Alternating Direction Method with Adaptive Penalty for Low-Rank Representation IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To address this issue, we propose a linearized ADM (LADM) method by linearizing the quadratic penalty term and adding a proximal term when solving the subproblems.	Zhouchen Lin; Risheng Liu; Zhixun Su;
2011	7	Im2Text: Describing Images Using 1 Million Captioned Photographs IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We develop and demonstrate automatic image description methods using a large captioned photo collection.	Vicente Ordonez; Girish Kulkarni; Tamara L. Berg;
2011	8	Co-regularized Multi-view Spectral Clustering IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a spectral clustering framework that achieves this goal by co-regularizing the clustering hypotheses, and propose two co-regularization schemes to accomplish this.	Abhishek Kumar; Piyush Rai; Hal Daume;
2011	9	Dynamic Pooling and Unfolding Recursive Autoencoders for Paraphrase Detection IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Richard Socher; Eric H. Huang; Jeffrey Pennin; Christopher D. Manning; Andrew Y. Ng;
2011	10	Non-Asymptotic Analysis of Stochastic Approximation Algorithms for Machine Learning IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We provide a non-asymptotic analysis of the convergence of two well-known algorithms, stochastic gradient descent (a.k.a.~Robbins-Monro algorithm) as well as a simple modification where iterates are averaged (a.k.a.~Polyak-Ruppert averaging).	Eric Moulines; Francis R. Bach;
2011	11	Distributed Delayed Stochastic Optimization IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Our main contribution is to show that for smooth stochastic problems, the delays are asymptotically negligible.	Alekh Agarwal; John C. Duchi;
2011	12	Convergence Rates of Inexact Proximal-Gradient Methods for Convex Optimization IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We consider the problem of optimizing the sum of a smooth convex function and a non-smooth convex function using proximal-gradient methods, where an error is present in the calculation of the gradient of the smooth term or in the proximity operator with respect to the second term.	Mark Schmidt; Nicolas L. Roux; Francis R. Bach;
2011	13	High-dimensional Regression with Noisy and Missing Data: Provable Guarantees with Non-convexity IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We study these issues in the context of high-dimensional sparse linear regression, and propose novel estimators for the cases of noisy, missing, and/or dependent data.	Po-ling Loh; Martin J. Wainwright;
2011	14	Semantic Labeling of 3D Point Clouds for Indoor Scenes IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we use this data to build 3D point clouds of full indoor scenes such as an office and address the task of semantic labeling of these 3D point clouds.	Hema S. Koppula; Abhishek Anand; Thorsten Joachims; Ashutosh Saxena;
2011	15	Iterative Learning for Reliable Crowdsourcing Systems IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we consider a general model of such rowdsourcing tasks, and pose the problem of minimizing the total price (i.e., number of task assignments) that must be paid to achieve a target overall reliability.	David R. Karger; Sewoong Oh; Devavrat Shah;
2010	1	Online Learning for Latent Dirichlet Allocation IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We develop an online variational Bayes (VB) algorithm for Latent Dirichlet Allocation (LDA).	Matthew Hoffman; Francis R. Bach; David M. Blei;
2010	2	Parallelized Stochastic Gradient Descent IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we present the first parallel stochastic gradient descent algorithm including a detailed analysis and experimental evidence.	Martin Zinkevich; Markus Weimer; Lihong Li; Alex J. Smola;
2010	3	Self-Paced Learning for Latent Variable Models IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To alleviate this problem, we build on the intuition that, rather than considering all samples simultaneously, the algorithm should be presented with the training data in a meaningful order that facilitates learning.	M. P. Kumar; Benjamin Packer; Daphne Koller;
2010	4	Double Q-learning IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce an alternative way to approximate the maximum expected value for any set of random variables.	Hado V. Hasselt;
2010	5	Learning To Count Objects in Images IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a new supervised learning framework for visual object counting tasks, such as estimating the number of cells in a microscopic image or the number of humans in surveillance video frames.	Victor Lempitsky; Andrew Zisserman;
2010	6	Monte-Carlo Planning in Large POMDPs IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper introduces a Monte-Carlo algorithm for online planning in large POMDPs.	David Silver; Joel Veness;
2010	7	The Multidimensional Wisdom of Crowds IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Peter Welinder; Steve Branson; Pietro Perona; Serge J. Belongie;
2010	8	Robust PCA Via Outlier Pursuit IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present an efficient convex optimization-based algorithm we call Outlier Pursuit, that under some mild assumptions on the uncorrupted points (satisfied, e.g., by the standard generative assumption in PCA problems) recovers the exact optimal low-dimensional subspace, and identifies the corrupted points.	Huan Xu; Constantine Caramanis; Sujay Sanghavi;
2010	9	Extended Bayesian Information Criteria for Gaussian Graphical Models IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we establish the asymptotic consistency of an extended Bayesian information criterion for Gaussian graphical models in a scenario where both the number of variables p and the sample size n grow.	Rina Foygel; Mathias Drton;
2010	10	Learning Convolutional Feature Hierarchies for Visual Recognition IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose an unsupervised method for learning multi-stage hierarchies of sparse convolutional features.	KORAY KAVUKCUOGLU et. al.
2010	11	Active Learning By Querying Informative and Representative Examples IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We address this challenge by a principled approach, termed QUIRE, based on the min-max view of active learning.	Sheng-jun Huang; Rong Jin; Zhi-Hua Zhou;
2010	12	Guaranteed Rank Minimization Via Singular Value Projection IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we propose a simple and fast algorithm SVP (Singular Value Projection) for rank minimization under affine constraints ARMP and show that SVP recovers the minimum rank solution for affine constraints that satisfy a Restricted Isometry Property} (RIP).	Prateek Jain; Raghu Meka; Inderjit S. Dhillon;
2010	13	Learning to Combine Foveal Glimpses with A Third-order Boltzmann Machine IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We describe a model based on a Boltzmann machine with third-order connections that can learn how to accumulate information about a shape over several fixations.	Hugo Larochelle; Geoffrey E. Hinton;
2010	14	Stability Approach to Regularization Selection (StARS) for High Dimensional Graphical Models IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we present StARS: a new stability-based method for choosing the regularization parameter in high dimensional inference for undirected graphs.	Han Liu; Kathryn Roeder; Larry Wasserman;
2010	15	Parametric Bandits: The Generalized Linear Case IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We pro- pose a new optimistic, UCB-like, algorithm for non-linearly parameterized bandit problems using the Generalized Linear Model (GLM) framework.	Sarah Filippi; Olivier Cappe; Aur�lien Garivier; Csaba Szepesv�ri;
2009	1	Reading Tea Leaves: How Humans Interpret Topic Models IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Jonathan Chang; Sean Gerrish; Chong Wang; Jordan L. Boyd-graber; David M. Blei;
2009	2	Fast Image Deconvolution Using Hyper-Laplacian Priors IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we describe a deconvolution approach that is several orders of magnitude faster than existing techniques that use hyper-Laplacian priors.	Dilip Krishnan; Rob Fergus;
2009	3	Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Matrices Via Convex Optimization IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper considers the idealized “robust principal component analysis” problem of recovering a low rank matrix A from corrupted observations D = A + E. Here, the error entries E can be arbitrarily large (modeling grossly corrupted observations common in visual and bioinformatic data), but are assumed to be sparse.	John Wright; Arvind Ganesh; Shankar Rao; Yigang Peng; Yi Ma;
2009	4	Whose Vote Should Count More: Optimal Integration of Labels from Labelers of Unknown Expertise IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper we present a probabilistic model and use it to simultaneously infer the label of each image, the expertise of each labeler, and the difficulty of each image.	Jacob Whitehill; Ting-fan Wu; Jacob Bergsma; Javier R. Movellan; Paul L. Ruvolo;
2009	5	Unsupervised Feature Learning for Audio Classification Using Convolutional Deep Belief Networks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we apply convolutional deep belief networks to audio data and empirically evaluate them on various audio classification tasks.	Honglak Lee; Peter Pham; Yan Largman; Andrew Y. Ng;
2009	6	Zero-shot Learning with Semantic Output Codes IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We consider the problem of zero-shot learning, where the goal is to learn a classifier $f: X \rightarrow Y$ that must predict novel values of $Y$ that were omitted from the training set.	Mark Palatucci; Dean Pomerleau; Geoffrey E. Hinton; Tom M. Mitchell;
2009	7	Learning to Hash with Binary Reconstructive Embeddings IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we develop an algorithm for learning hash functions based on explicitly minimizing the reconstruction error between the original distances and the Hamming distances of the corresponding binary embeddings.	Brian Kulis; Trevor Darrell;
2009	8	Nonlinear Learning Using Local Coordinate Coding IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper introduces a new method for semi-supervised learning on high dimensional nonlinear manifolds, which includes a phase of unsupervised basis learning and a phase of supervised function learning.	Kai Yu; Tong Zhang; Yihong Gong;
2009	9	Rethinking LDA: Why Priors Matter IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we explore several classes of structured priors for topic models.	Hanna M. Wallach; David M. Mimno; Andrew McCallum;
2009	10	Matrix Completion from Noisy Entries IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Given a matrix M of low-rank, we consider the problem of reconstructing it from noisy observations of a small, random subset of its entries.	Raghunandan Keshavan; Andrea Montanari; Sewoong Oh;
2009	11	Kernel Methods for Deep Learning IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce a new family of positive-definite kernel functions that mimic the computation in large, multilayer neural nets. On several problems, we obtain better results than previous, leading benchmarks from both SVMs with Gaussian kernels as well as deep belief nets.	Youngmin Cho; Lawrence K. Saul;
2009	12	Locality-sensitive Binary Codes from Shift-invariant Kernels IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a full theoretical analysis of the convergence properties of the proposed scheme, and report favorable experimental performance as compared to a recent state-of-the-art method, spectral hashing.	Maxim Raginsky; Svetlana Lazebnik;
2009	13	Replicated Softmax: An Undirected Topic Model IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We describe efficient inference and learning procedures for such a family.	Geoffrey E. Hinton; Russ R. Salakhutdinov;
2009	14	On The Convergence of The Concave-Convex Procedure IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we follow a different reasoning and show how Zangwills global convergence theory of iterative algorithms provides a natural framework to prove the convergence of CCCP, allowing a more elegant and simple proof. We also present an open problem on the issue of local convergence of CCCP.	Gert R. Lanckriet; Bharath K. Sriperumbudur;
2009	15	Measuring Invariances in Deep Networks IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a number of empirical tests that directly measure the degree to which these learned features are invariant to different image transforms.	Ian Goodfellow; Honglak Lee; Quoc V. Le; Andrew Saxe; Andrew Y. Ng;
2008	1	Spectral Hashing IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we show that the problem of finding a best code for a given dataset is closely related to the problem of graph partitioning and can be shown to be NP hard.	Yair Weiss; Antonio Torralba; Rob Fergus;
2008	2	Mixed Membership Stochastic Blockmodels IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we describe a class of latent variable models of such data called Mixed Membership Stochastic Blockmodels.	Edo M. Airoldi; David M. Blei; Stephen E. Fienberg; Eric P. Xing;
2008	3	Near-optimal Regret Bounds for Reinforcement Learning IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In order to describe the transition structure of an MDP we propose a new parameter: An MDP has diameter D if for any pair of states s1,s2 there is a policy which moves from s1 to s2 in at most D steps (on average).	Peter Auer; Thomas Jaksch; Ronald Ortner;
2008	4	Supervised Dictionary Learning IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper proposes a new step in that direction with a novel sparse representation for signals belonging to different classes in terms of a shared dictionary and multiple decision functions.	Julien Mairal; Jean Ponce; Guillermo Sapiro; Andrew Zisserman; Francis R. Bach;
2008	5	A Scalable Hierarchical Distributed Language Model IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce a fast hierarchical language model along with a simple feature-based algorithm for automatic construction of word trees from the data.	Andriy Mnih; Geoffrey E. Hinton;
2008	6	Natural Image Denoising with Convolutional Networks IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present an approach to low-level vision that combines two main ideas: the use of convolutional networks as an image processing architecture and an unsupervised learning procedure that synthesizes training samples from specific noise models.	Viren Jain; Sebastian Seung;
2008	7	Nonlinear Causal Discovery with Additive Noise Models IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this contribution we show that in fact the basic linear framework can be generalized to nonlinear models with additive noise.	Patrik O. Hoyer; Dominik Janzing; Joris M. Mooij; Jonas Peters; Bernhard Sch�lkopf;
2008	8	Policy Search for Motor Primitives in Robotics IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we extend previous work on policy learning from the immediate reward case to episodic reinforcement learning.	Jens Kober; Jan R. Peters;
2008	9	Gaussian-process Factor Analysis for Low-dimensional Single-trial Analysis of Neural Population Activity IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We consider the problem of extracting smooth low-dimensional “neural trajectories” that summarize the activity recorded simultaneously from tens to hundreds of neurons on individual experimental trials.	BYRON M. YU et. al.
2008	10	Privacy-preserving Logistic Regression IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper addresses the important tradeoff between privacy and learnability, when designing algorithms for learning from private databases.	Kamalika Chaudhuri; Claire Monteleoni;
2008	11	Dynamic Visual Attention: Searching for Coding Length Increments IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, a dynamic visual attention model based on the rarity of features is proposed.	Xiaodi Hou; Liqing Zhang;
2008	12	Weighted Sums of Random Kitchen Sinks: Replacing Minimization with Randomization in Learning IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: “I am training a randomly wired neural net to play tic-tac-toe,” Sussman replied.	Ali Rahimi; Benjamin Recht;
2008	13	Clustered Multi-Task Learning: A Convex Formulation IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we assume that tasks are clustered into groups, which are unknown beforehand, and that tasks within a group have similar weight vectors.	Laurent Jacob; Jean-philippe Vert; Francis R. Bach;
2008	14	Domain Adaptation with Multiple Sources IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents a theoretical analysis of the problem of adaptation with multiple sources.	Yishay Mansour; Mehryar Mohri; Afshin Rostamizadeh;
2008	15	Sparse Online Learning Via Truncated Gradient IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a general method called truncated gradient to induce sparsity in the weights of online-learning algorithms with convex loss.	John Langford; Lihong Li; Tong Zhang;
2007	1	Probabilistic Matrix Factorization IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Andriy Mnih; Russ R. Salakhutdinov;
2007	2	Random Features for Large-Scale Kernel Machines IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Ali Rahimi; Benjamin Recht;
2007	3	Supervised Topic Models IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce supervised latent Dirichlet allocation (sLDA), a statistical model of labelled documents.	Jon D. Mcauliffe; David M. Blei;
2007	4	The Tradeoffs of Large Scale Learning IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This contribution develops a theoretical framework that takes into account the effect of approximate optimization on learning algorithms.	L�on Bottou; Olivier Bousquet;
2007	5	Sparse Deep Belief Net Model for Visual Area V2 IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper presents an unsupervised learning model that faithfully mimics certain properties of visual area V2.	Honglak Lee; Chaitanya Ekanadham; Andrew Y. Ng;
2007	6	Multi-task Gaussian Process Prediction IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Edwin V. Bonilla; Kian M. Chai; Christopher Williams;
2007	7	Sparse Feature Learning for Deep Belief Networks IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Unsupervised learning algorithms aim to discover the structure hidden in the data, and to learn representations that are more suitable as input to a supervised machine than the raw input.	Marc’aurelio Ranzato; Y-lan Boureau; Yann L. Cun;
2007	8	Direct Importance Estimation with Model Selection and Its Application to Covariate Shift Adaptation IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this paper, we propose a direct importance estimation method that does not require the input density estimates.	Masashi Sugiyama; Shinichi Nakajima; Hisashi Kashima; Paul V. Buenau; Motoaki Kawanabe;
2007	9	A Kernel Statistical Test of Independence IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	ARTHUR GRETTON et. al.
2007	10	Regret Minimization in Games with Incomplete Information IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Martin Zinkevich; Michael Johanson; Michael Bowling; Carmelo Piccione;
2007	11	Multiple-Instance Active Learning IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a framework for active learning in the multiple-instance setting.	Burr Settles; Mark Craven; Soumya Ray;
2007	12	The Epoch-Greedy Algorithm for Multi-armed Bandits with Side Information IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present Epoch-Greedy, an algorithm for multi-armed bandits with observable side information.	John Langford; Tong Zhang;
2007	13	Kernel Measures of Conditional Dependence IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Kenji Fukumizu; Arthur Gretton; Xiaohai Sun; Bernhard Sch�lkopf;
2007	14	Predicting Human Gaze Using Low-level Saliency Combined with Face Detection IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this study we recorded eye-movements of human observers while they viewed photographs of natural scenes.	Moran Cerf; Jonathan Harel; Wolfgang Einhaeuser; Christof Koch;
2007	15	McRank: Learning to Rank Using Multiple Classification and Gradient Boosting IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Ping Li; Qiang Wu; Christopher J. Burges;
2006	1	Greedy Layer-Wise Training of Deep Networks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Yoshua Bengio; Pascal Lamblin; Dan Popovici; Hugo Larochelle;
2006	2	Graph-Based Visual Saliency IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Jonathan Harel; Christof Koch; Pietro Perona;
2006	3	Efficient Sparse Coding Algorithms IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Honglak Lee; Alexis Battle; Rajat Raina; Andrew Y. Ng;
2006	4	A Kernel Method for The Two-Sample-Problem IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Arthur Gretton; Karsten Borgwardt; Malte Rasch; Bernhard Sch�lkopf; Alex J. Smola;
2006	5	Analysis of Representations for Domain Adaptation IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Shai Ben-David; John Blitzer; Koby Crammer; Fernando Pereira;
2006	6	Correcting Sample Selection Bias By Unlabeled Data IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Jiayuan Huang; Arthur Gretton; Karsten Borgwardt; Bernhard Sch�lkopf; Alex J. Smola;
2006	7	Multi-Task Feature Learning IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Andreas Argyriou; Theodoros Evgeniou; Massimiliano Pontil;
2006	8	Efficient Learning of Sparse Representations with An Energy-Based Model IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Marc’aurelio Ranzato; Christopher Poultney; Sumit Chopra; Yann L. Cun;
2006	9	Map-Reduce for Machine Learning on Multicore IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	CHENG-TAO CHU et. al.
2006	10	Learning with Hypergraphs: Clustering, Classification, and Embedding IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Dengyong Zhou; Jiayuan Huang; Bernhard Sch�lkopf;
2006	11	Sparse Representation for Signal Classification IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Ke Huang; Selin Aviyente;
2006	12	Learning to Rank with Nonsmooth Cost Functions IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Christopher J. Burges; Robert Ragno; Quoc V. Le;
2006	13	Modeling Human Motion Using Binary Latent Variables IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Graham W. Taylor; Geoffrey E. Hinton; Sam T. Roweis;
2006	14	An Application of Reinforcement Learning to Aerobatic Helicopter Flight IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Pieter Abbeel; Adam Coates; Morgan Quigley; Andrew Y. Ng;
2006	15	Fast Discriminative Visual Codebooks Using Randomized Clustering Forests IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Frank Moosmann; Bill Triggs; Frederic Jurie;
2005	1	Distance Metric Learning For Large Margin Nearest Neighbor Classification IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View	Kilian Q. Weinberger; John Blitzer; Lawrence K. Saul;
2005	2	Laplacian Score For Feature Selection IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Xiaofei He; Deng Cai; Partha Niyogi;
2005	3	Sparse Gaussian Processes Using Pseudo-inputs IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Edward Snelson; Zoubin Ghahramani;
2005	4	Bayesian Surprise Attracts Human Attention IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Laurent Itti; Pierre F. Baldi;
2005	5	Saliency Based On Information Maximization IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Neil Bruce; John Tsotsos;
2005	6	Correlated Topic Models IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	John D. Lafferty; David M. Blei;
2005	7	Learning Depth From Single Monocular Images IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Ashutosh Saxena; Sung H. Chung; Andrew Y. Ng;
2005	8	Infinite Latent Feature Models And The Indian Buffet Process IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Zoubin Ghahramani; Thomas L. Griffiths;
2005	9	Multiple Instance Boosting For Object Detection IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Cha Zhang; John C. Platt; Paul A. Viola;
2005	10	Metric Learning By Collapsing Classes IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Amir Globerson; Sam T. Roweis;
2005	11	An Application Of Markov Random Fields To Range Sensing IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	James Diebel; Sebastian Thrun;
2005	12	Off-Road Obstacle Avoidance Through End-to-End Learning IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Urs Muller; Jan Ben; Eric Cosatto; Beat Flepp; Yann L. Cun;
2005	13	Subsequence Kernels For Relation Extraction IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Raymond J. Mooney; Razvan C. Bunescu;
2005	14	Gaussian Process Dynamical Models IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Jack Wang; Aaron Hertzmann; David J. Fleet;
2005	15	Generalized Nonnegative Matrix Approximations With Bregman Divergences IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Suvrit Sra; Inderjit S. Dhillon;
2004	1	Self-Tuning Spectral Clustering IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Lihi Zelnik-manor; Pietro Perona;
2004	2	Neighbourhood Components Analysis IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Jacob Goldberger; Geoffrey E. Hinton; Sam T. Roweis; Russ R. Salakhutdinov;
2004	3	Semi-supervised Learning By Entropy Minimization IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Yves Grandvalet; Yoshua Bengio;
2004	4	Maximum-Margin Matrix Factorization IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Nathan Srebro; Jason Rennie; Tommi S. Jaakkola;
2004	5	A Direct Formulation For Sparse PCA Using Semidefinite Programming IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Alexandre D’aspremont; Laurent E. Ghaoui; Michael I. Jordan; Gert R. Lanckriet;
2004	6	Learning Syntactic Patterns For Automatic Hypernym Discovery IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Rion Snow; Daniel Jurafsky; Andrew Y. Ng;
2004	7	Maximum Likelihood Estimation Of Intrinsic Dimension IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Elizaveta Levina; Peter J. Bickel;
2004	8	Intrinsically Motivated Reinforcement Learning IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Nuttapong Chentanez; Andrew G. Barto; Satinder P. Singh;
2004	9	Semi-Markov Conditional Random Fields For Information Extraction IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Sunita Sarawagi; William W. Cohen;
2004	10	The Entire Regularization Path For The Support Vector Machine IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Saharon Rosset; Robert Tibshirani; Ji Zhu; Trevor J. Hastie;
2004	11	Two-Dimensional Linear Discriminant Analysis IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Jieping Ye; Ravi Janardan; Qi Li;
2004	12	Result Analysis Of The NIPS 2003 Feature Selection Challenge IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Isabelle Guyon; Steve Gunn; Asa Ben-Hur; Gideon Dror;
2004	13	Integrating Topics And Syntax IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Thomas L. Griffiths; Mark Steyvers; David M. Blei; Joshua B. Tenenbaum;
2004	14	An Investigation Of Practical Approximate Nearest Neighbor Algorithms IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Ting Liu; Andrew W. Moore; Ke Yang; Alexander G. Gray;
2004	15	Parallel Support Vector Machines: The Cascade SVM IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Hans P. Graf; Eric Cosatto; L�on Bottou; Igor Dourdanovic; Vladimir Vapnik;
2003	1	Locality Preserving Projections IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Xiaofei He; Partha Niyogi;
2003	2	Learning With Local And Global Consistency IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Dengyong Zhou; Olivier Bousquet; Thomas N. Lal; Jason Weston; Bernhard Sch�lkopf;
2003	3	Probability Estimates For Multi-Class Classification By Pairwise Coupling IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Ting-fan Wu; Chih-jen Lin; Ruby C. Weng;
2003	4	Online Passive-Aggressive Algorithms IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Shai Shalev-shwartz; Koby Crammer; Ofer Dekel; Yoram Singer;
2003	5	Max-Margin Markov Networks IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Ben Taskar; Carlos Guestrin; Daphne Koller;
2003	6	Hierarchical Topic Models And The Nested Chinese Restaurant Process IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Thomas L. Griffiths; Michael I. Jordan; Joshua B. Tenenbaum; David M. Blei;
2003	7	Out-of-Sample Extensions For LLE, Isomap, MDS, Eigenmaps, And Spectral Clustering IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	YOSHUA BENGIO et. al.
2003	8	1-norm Support Vector Machines IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Ji Zhu; Saharon Rosset; Robert Tibshirani; Trevor J. Hastie;
2003	9	Learning The K In K-means IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Greg Hamerly; Charles Elkan;
2003	10	Efficient And Robust Feature Extraction By Maximum Margin Criterion IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Haifeng Li; Tao Jiang; Keshu Zhang;
2003	11	When Does Non-Negative Matrix Factorization Give A Correct Decomposition Into Parts? IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	David Donoho; Victoria Stodden;
2003	12	A Model For Learning The Semantics Of Pictures IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Victor Lavrenko; R. Manmatha; Jiwoon Jeon;
2003	13	Gaussian Process Latent Variable Models For Visualisation Of High Dimensional Data IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Neil D. Lawrence;
2003	14	Ranking On Data Manifolds IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Dengyong Zhou; Jason Weston; Arthur Gretton; Olivier Bousquet; Bernhard Sch�lkopf;
2003	15	*ARA: Anytime A* With Provable Bounds On Sub-Optimality IF:8** Related Papers Related Patents Related Grants Related Venues Related Experts View	Maxim Likhachev; Geoffrey J. Gordon; Sebastian Thrun;
2002	1	Distance Metric Learning With Application To Clustering With Side-Information IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Eric P. Xing; Michael I. Jordan; Stuart J. Russell; Andrew Y. Ng;
2002	2	Stochastic Neighbor Embedding IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Geoffrey E. Hinton; Sam T. Roweis;
2002	3	Support Vector Machines For Multiple-Instance Learning IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Stuart Andrews; Ioannis Tsochantaridis; Thomas Hofmann;
2002	4	Global Versus Local Methods In Nonlinear Dimensionality Reduction IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Vin D. Silva; Joshua B. Tenenbaum;
2002	5	Fast Exact Inference With A Factored Model For Natural Language Parsing IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Dan Klein; Christopher D. Manning;
2002	6	Learning Attractor Landscapes For Learning Motor Primitives IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Auke J. Ijspeert; Jun Nakanishi; Stefan Schaal;
2002	7	An Impossibility Theorem For Clustering IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Jon M. Kleinberg;
2002	8	Adaptive Nonlinear System Identification With Echo State Networks IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Herbert Jaeger;
2002	9	Fast Sparse Gaussian Process Methods: The Informative Vector Machine IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Ralf Herbrich; Neil D. Lawrence; Matthias Seeger;
2002	10	Recovering Intrinsic Images From A Single Image IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Marshall F. Tappen; William T. Freeman; Edward H. Adelson;
2002	11	Cluster Kernels For Semi-Supervised Learning IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Olivier Chapelle; Jason Weston; Bernhard Sch�lkopf;
2002	12	Charting A Manifold IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Matthew Brand;
2002	13	Ranking With Large Margin Principle: Two Approaches IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Amnon Shashua; Anat Levin;
2002	14	Parametric Mixture Models For Multi-Labeled Text IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Naonori Ueda; Kazumi Saito;
2002	15	Fast Kernels For String And Tree Matching IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Alex J. Smola; S.v.n. Vishwanathan;
2001	1	Latent Dirichlet Allocation IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View	David M. Blei; Andrew Y. Ng; Michael I. Jordan;
2001	2	On Spectral Clustering: Analysis And An Algorithm IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Andrew Y. Ng; Michael I. Jordan; Yair Weiss;
2001	3	Laplacian Eigenmaps And Spectral Techniques For Embedding And Clustering IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Mikhail Belkin; Partha Niyogi;
2001	4	On Discriminative Vs. Generative Classifiers: A Comparison Of Logistic Regression And Naive Bayes IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Andrew Y. Ng; Michael I. Jordan;
2001	5	A Kernel Method For Multi-labelled Classification IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Andr� Elisseeff; Jason Weston;
2001	6	On Kernel-Target Alignment IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Nello Cristianini; John Shawe-Taylor; Andr� Elisseeff; Jaz S. Kandola;
2001	7	Online Learning With Kernels IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Jyrki Kivinen; Alex J. Smola; Robert C. Williamson;
2001	8	A Natural Policy Gradient IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Sham M. Kakade;
2001	9	Convolution Kernels For Natural Language IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Michael Collins; Nigel Duffy;
2001	10	EM-DD: An Improved Multiple-Instance Learning Technique IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Qi Zhang; Sally A. Goldman;
2001	11	Partially Labeled Classification With Markov Random Walks IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Martin Szummer; Tommi Jaakkola;
2001	12	Spectral Relaxation For K-means Clustering IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Hongyuan Zha; Xiaofeng He; Chris Ding; Ming Gu; Horst D. Simon;
2001	13	Pranking With Ranking IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Koby Crammer; Yoram Singer;
2001	14	The Infinite Hidden Markov Model IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Matthew J. Beal; Zoubin Ghahramani; Carl E. Rasmussen;
2001	15	Fast And Robust Classification Using Asymmetric AdaBoost And A Detector Cascade IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Paul Viola; Michael Jones;
2000	1	Algorithms For Non-negative Matrix Factorization IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Two different multi- plicative algorithms for NMF are analyzed.	Daniel D. Lee; H. Sebastian Seung;
2000	2	A Neural Probabilistic Language Model IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View	Yoshua Bengio; R�jean Ducharme; Pascal Vincent;
2000	3	The Unscented Particle Filter IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Rudolph van der Merwe; Arnaud Doucet; Nando de Freitas; Eric A. Wan;
2000	4	Text Classification Using String Kernels IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Huma Lodhi; John Shawe-Taylor; Nello Cristianini; Christopher J. C. H. Watkins;
2000	5	Incremental And Decremental Support Vector Machine Learning IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Gert Cauwenberghs; Tomaso Poggio;
2000	6	Feature Selection For SVMs IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	JASON WESTON et. al.
2000	7	Generalized Belief Propagation IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Jonathan S. Yedidia; William T. Freeman; Yair Weiss;
2000	8	Overfitting In Neural Nets: Backpropagation, Conjugate Gradient, And Early Stopping IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Rich Caruana; Steve Lawrence; C. Lee Giles;
2000	9	Shape Context: A New Descriptor For Shape Matching And Object Recognition IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Serge Belongie; Jitendra Malik; Jan Puzicha;
2000	10	The Kernel Trick For Distances IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Bernhard Sch�lkopf;
2000	11	Automatic Choice Of Dimensionality For PCA IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Thomas P. Minka;
2000	12	The Missing Link – A Probabilistic Model Of Document Content And Hypertext Connectivity IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	David A. Cohn; Thomas Hofmann;
2000	13	One Microphone Source Separation IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Sam T. Roweis;
2000	14	Learning Segmentation By Random Walks IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Marina Meila; Jianbo Shi;
2000	15	Sparse Greedy Gaussian Process Regression IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Alex J. Smola; Peter L. Bartlett;
1999	1	Policy Gradient Methods For Reinforcement Learning With Function Approximation IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Richard S. Sutton; David A. McAllester; Satinder P. Singh; Yishay Mansour;
1999	2	Actor-Critic Algorithms IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Vijay R. Konda; John N. Tsitsiklis;
1999	3	Large Margin DAGs For Multiclass Classification IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	John C. Platt; Nello Cristianini; John Shawe-Taylor;
1999	4	Support Vector Method For Novelty Detection IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Bernhard Sch�lkopf; Robert C. Williamson; Alex J. Smola; John Shawe-Taylor; John C. Platt;
1999	5	The Infinite Gaussian Mixture Model IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Carl Edward Rasmussen;
1999	6	The Relevance Vector Machine IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Michael E. Tipping;
1999	7	Inference For The Generalization Error IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Claude Nadeau; Yoshua Bengio;
1999	8	A Variational Baysian Framework For Graphical Models IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Hagai Attias;
1999	9	Boosting Algorithms As Gradient Descent IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Llew Mason; Jonathan Baxter; Peter L. Bartlett; Marcus R. Frean;
1999	10	Correctness Of Belief Propagation In Gaussian Graphical Models Of Arbitrary Topology IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Yair Weiss; William T. Freeman;
1999	11	Bayesian Map Learning In Dynamic Environments IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Kevin P. Murphy;
1999	12	Scale Mixtures Of Gaussians And The Statistics Of Natural Images IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Martin J. Wainwright; Eero P. Simoncelli;
1999	13	Variational Inference For Bayesian Mixtures Of Factor Analysers IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Zoubin Ghahramani; Matthew J. Beal;
1999	14	Agglomerative Information Bottleneck IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Noam Slonim; Naftali Tishby;
1999	15	Model Selection For Support Vector Machines IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Olivier Chapelle; Vladimir Vapnik;
1998	1	Exploiting Generative Models In Discriminative Classifiers IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Tommi Jaakkola; David Haussler;
1998	2	Kernel PCA And De-Noising In Feature Spaces IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	SEBASTIAN MIKA et. al.
1998	3	Semi-Supervised Support Vector Machines IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Kristin P. Bennett; Ayhan Demiriz;
1998	4	Support Vector Machines Applied To Face Recognition IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	P. Jonathon Phillips;
1998	5	SMEM Algorithm For Mixture Models IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Naonori Ueda; Ryohei Nakano; Zoubin Ghahramani; Geoffrey E. Hinton;
1998	6	Using Analytic QP And Sparseness To Speed Training Of Support Vector Machines IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	John C. Platt;
1998	7	Bayesian PCA IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Christopher M. Bishop;
1998	8	Gradient Descent For General Reinforcement Learning IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Leemon C. Baird III; Andrew W. Moore;
1998	9	Learning Nonlinear Dynamical Systems Using An EM Algorithm IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	Zoubin Ghahramani; Sam T. Roweis;
1998	10	Finite-Sample Convergence Rates For Q-Learning And Indirect Algorithms IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	Michael J. Kearns; Satinder P. Singh;
1998	11	Shrinking The Tube: A New Support Vector Regression Algorithm IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	Bernhard Sch�lkopf; Peter L. Bartlett; Alex J. Smola; Robert C. Williamson;
1998	12	Bayesian Modeling Of Human Concept Learning IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	Joshua B. Tenenbaum;
1998	13	Very Fast EM-Based Mixture Model Clustering Using Multiresolution Kd-Trees IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	Andrew W. Moore;
1998	14	Dynamically Adapting Kernels In Support Vector Machines IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	Nello Cristianini; Colin Campbell; John Shawe-Taylor;
1998	15	Classification On Pairwise Proximity Data IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	Thore Graepel; Ralf Herbrich; Peter Bollmann-Sdorra; Klaus Obermayer;
1997	1	Classification By Pairwise Coupling IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Trevor Hastie; Robert Tibshirani;
1997	2	A Framework For Multiple-Instance Learning IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Oded Maron; Tom�s Lozano-P�rez;
1997	3	EM Algorithms For PCA And SPCA IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Sam T. Roweis;
1997	4	Reinforcement Learning With Hierarchies Of Machines IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Ronald Parr; Stuart J. Russell;
1997	5	Intrusion Detection With Neural Networks IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Jake Ryan; Meng-Jang Lin; Risto Miikkulainen;
1997	6	Extended ICA Removes Artifacts From Electroencephalographic Recordings IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	TZYY-PING JUNG et. al.
1997	7	New Approximations Of Differential Entropy For Independent Component Analysis And Projection Pursuit IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Aapo Hyv�rinen;
1997	8	Refractoriness And Neural Precision IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Michael J. Berry II; Markus Meister;
1997	9	A Revolution: Belief Propagation In Graphs With Cycles IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Brendan J. Frey; David J. C. MacKay;
1997	10	Prior Knowledge In Support Vector Kernels IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Bernhard Sch�lkopf; Patrice Simard; Alex J. Smola; Vladimir Vapnik;
1997	11	Mapping A Manifold Of Perceptual Observations IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Joshua B. Tenenbaum;
1997	12	Regression With Input-dependent Noise: A Gaussian Process Treatment IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	Paul W. Goldberg; Christopher K. I. Williams; Christopher M. Bishop;
1997	13	Independent Component Analysis For Identification Of Artifacts In Magnetoencephalographic Recordings IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	Ricardo Vig�rio; Veikko Jousm�ki; Matti H�m�l�inen; Riitta Hari; Erkki Oja;
1997	14	Monotonic Networks IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	Joseph Sill;
1997	15	Dynamic Stochastic Synapses As Computational Units IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	Wolfgang Maass; Anthony M. Zador;
1996	1	Support Vector Regression Machines IF:10 Related Papers Related Patents Related Grants Related Venues Related Experts View	Harris Drucker; Christopher J. C. Burges; Linda Kaufman; Alex J. Smola; Vladimir Vapnik;
1996	2	Support Vector Method For Function Approximation, Regression Estimation And Signal Processing IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Vladimir Vapnik; Steven E. Golowich; Alex J. Smola;
1996	3	Analysis Of Temporal-Diffference Learning With Function Approximation IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	John N. Tsitsiklis; Benjamin Van Roy;
1996	4	LSTM Can Solve Hard Long Time Lag Problems IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Sepp Hochreiter; J�rgen Schmidhuber;
1996	5	MIMIC: Finding Optima By Estimating Probability Densities IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Jeremy S. De Bonet; Charles Lee Isbell Jr.; Paul A. Viola;
1996	6	Clustering Sequences With Hidden Markov Models IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Padhraic Smyth;
1996	7	Probabilistic Interpretation Of Population Codes IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Richard S. Zemel; Peter Dayan; Alexandre Pouget;
1996	8	Improving The Accuracy And Speed Of Support Vector Machines IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Christopher J. C. Burges; Bernhard Sch�lkopf;
1996	9	Practical Confidence And Prediction Intervals IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Tom Heskes;
1996	10	A Mixture Of Experts Classifier With Learning Based On Both Labelled And Unlabelled Data IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	David J. Miller; Hasan S. Uyar;
1996	11	Clustering Via Concave Minimization IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Paul S. Bradley; Olvi L. Mangasarian; W. Nick Street;
1996	12	Computing With Infinite Networks IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	Christopher K. I. Williams;
1996	13	Reinforcement Learning For Dynamic Channel Allocation In Cellular Telephone Systems IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	Satinder P. Singh; Dimitri P. Bertsekas;
1996	14	For Valid Generalization The Size Of The Weights Is More Important Than The Size Of The Network IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	Peter L. Bartlett;
1996	15	Blind Separation Of Delayed And Convolved Sources IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	Te-Won Lee; Anthony J. Bell; Russell H. Lambert;
1995	1	A New Learning Algorithm For Blind Signal Separation IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Shun-ichi Amari; Andrzej Cichocki; Howard Hua Yang;
1995	2	Independent Component Analysis Of Electroencephalographic Data IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Scott Makeig; Anthony J. Bell; Tzyy-Ping Jung; Terrence J. Sejnowski;
1995	3	Generalization In Reinforcement Learning: Successful Examples Using Sparse Coarse Coding IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Richard S. Sutton;
1995	4	Gaussian Processes For Regression IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Christopher K. I. Williams; Carl Edward Rasmussen;
1995	5	Reinforcement Learning By Probability Matching IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Philip N. Sabes; Michael I. Jordan;
1995	6	Is Learning The N-th Thing Any Easier Than Learning The First? IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Sebastian Thrun;
1995	7	Extracting Tree-Structured Representations Of Trained Networks IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Mark Craven; Jude W. Shavlik;
1995	8	Factorial Hidden Markov Models IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Zoubin Ghahramani; Michael I. Jordan;
1995	9	Improving Elevator Performance Using Reinforcement Learning IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Robert H. Crites; Andrew G. Barto;
1995	10	Generalized Learning Vector Quantization IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Atsushi Sato; Keiji Yamada;
1995	11	Human Face Detection In Visual Scenes IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Henry A. Rowley; Shumeet Baluja; Takeo Kanade;
1995	12	Learning With Ensembles: How Overfitting Can Be Useful IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Peter Sollich; Anders Krogh;
1995	13	Generating Accurate And Diverse Members Of A Neural-Network Ensemble IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	David W. Opitz; Jude W. Shavlik;
1995	14	Hierarchical Recurrent Neural Networks For Long-Term Dependencies IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Salah El Hihi; Yoshua Bengio;
1995	15	Exploiting Tractable Substructures In Intractable Networks IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Lawrence K. Saul; Michael I. Jordan;
1994	1	Active Learning With Statistical Models IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	David A. Cohn; Zoubin Ghahramani; Michael I. Jordan;
1994	2	Neural Network Ensembles, Cross Validation, And Active Learning IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Anders Krogh; Jesper Vedelsby;
1994	3	A Growing Neural Gas Network Learns Topologies IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Bernd Fritzke;
1994	4	Generalization In Reinforcement Learning: Safely Approximating The Value Function IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Justin A. Boyan; Andrew W. Moore;
1994	5	New Algorithms For 2D And 3D Point Matching: Pose Estimation And Correspondence IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Steven Gold; Chien-Ping Lu; Anand Rangarajan; Suguna Pappu; Eric Mjolsness;
1994	6	Convergence Properties Of The K-Means Algorithms IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	L�on Bottou; Yoshua Bengio;
1994	7	Reinforcement Learning Algorithm For Partially Observable Markov Decision Problems IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Tommi Jaakkola; Satinder P. Singh; Michael I. Jordan;
1994	8	Reinforcement Learning With Soft State Aggregation IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Satinder P. Singh; Tommi Jaakkola; Michael I. Jordan;
1994	9	An Input Output HMM Architecture IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Yoshua Bengio; Paolo Frasconi;
1994	10	Reinforcement Learning Methods For Continuous-Time Markov Decision Problems IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Steven J. Bradtke; Michael O. Duff;
1994	11	Inferring Ground Truth From Subjective Labelling Of Venus Images IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Padhraic Smyth; Usama M. Fayyad; Michael C. Burl; Pietro Perona; Pierre Baldi;
1994	12	Learning Many Related Tasks At The Same Time With Backpropagation IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Rich Caruana;
1994	13	An Alternative Model For Mixtures Of Experts IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	Lei Xu; Michael I. Jordan; Geoffrey E. Hinton;
1994	14	Finding Structure In Reinforcement Learning IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	Sebastian Thrun; Anton Schwartz;
1994	15	Learning To Play The Game Of Chess IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	Sebastian Thrun;
1993	1	Autoencoders, Minimum Description Length And Helmholtz Free Energy IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Geoffrey E. Hinton; Richard S. Zemel;
1993	2	Statistics Of Natural Images: Scaling In The Woods IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Daniel L. Ruderman; William Bialek;
1993	3	Packet Routing In Dynamically Changing Networks: A Reinforcement Learning Approach IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	Justin A. Boyan; Michael L. Littman;
1993	4	Supervised Learning From Incomplete Data Via An EM Approach IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Zoubin Ghahramani; Michael I. Jordan;
1993	5	Neural Network Exploration Using Optimal Experiment Design IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	David A. Cohn;
1993	6	When Will A Genetic Algorithm Outperform Hill Climbing IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Melanie Mitchell; John H. Holland; Stephanie Forrest;
1993	7	Non-Intrusive Gaze Tracking Using Artificial Neural Networks IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Shumeet Baluja; Dean Pomerleau;
1993	8	Hoeffding Races: Accelerating Model Selection Search For Classification And Function Approximation IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Oded Maron; Andrew W. Moore;
1993	9	Learning Classification With Unlabeled Data IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	Virginia R. de Sa;
1993	10	Bayesian Modeling And Classification Of Neural Signals IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	Michael S. Lewicki;
1993	11	The Parti-Game Algorithm For Variable Resolution Reinforcement Learning In Multidimensional State-Spaces IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	Andrew W. Moore;
1993	12	Temporal Difference Learning Of Position Evaluation In The Game Of Go IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	Nicol N. Schraudolph; Peter Dayan; Terrence J. Sejnowski;
1993	13	Optimal Brain Surgeon: Extensions And Performance Comparisons IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	Babak Hassibi; David G. Stork; Gregory Wolff;
1993	14	Learning Curves: Asymptotic Values And Rate Of Convergence IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	Corinna Cortes; L. D. Jackel; Sara A. Solla; Vladimir Vapnik; John S. Denker;
1993	15	Surface Learning With Applications To Lipreading IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	Christoph Bregler; Stephen M. Omohundro;
1992	1	Second Order Derivatives For Network Pruning: Optimal Brain Surgeon IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Babak Hassibi; David G. Stork;
1992	2	Feudal Reinforcement Learning IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Peter Dayan; Geoffrey E. Hinton;
1992	3	Efficient Pattern Recognition Using A New Transformation Distance IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Patrice Simard; Yann LeCun; John S. Denker;
1992	4	An Information-Theoretic Approach To Deciphering The Hippocampal Code IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	William E. Skaggs; Bruce L. McNaughton; Katalin M. Gothard;
1992	5	Discriminability-Based Transfer Between Neural Networks IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	L. Y. Pratt;
1992	6	Word Space IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Hinrich Sch�tze;
1992	7	Non-Linear Dimensionality Reduction IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	David DeMers; Garrison W. Cottrell;
1992	8	Silicon Auditory Processors As Computer Peripherals IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	John Lazzaro; John Wawrzynek; M. Mahowald; Massimo Sivilotti; Dave Gillespie;
1992	9	Bayesian Learning Via Stochastic Dynamics IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	Radford M. Neal;
1992	10	Automatic Capacity Tuning Of Very Large VC-Dimension Classifiers IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	I. Guyon; B. Boser; V. Vapnik;
1992	11	Improving Performance In Neural Networks Using A Boosting Algorithm IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	Harris Drucker; Robert Schapire; Patrice Simard;
1992	12	A Fast Stochastic Error-Descent Algorithm For Supervised Learning And Optimization IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	Gert Cauwenberghs;
1992	13	Explanation-Based Neural Network Learning For Robot Control IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	Tom M. Mitchell; Sebastian B. Thrun;
1992	14	Reinforcement Learning Applied To Linear Quadratic Regulation IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	Steven J. Bradtke;
1992	15	Information, Prediction, And Query By Committee IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	Yoav Freund; H. Sebastian Seung; Eli Shamir; Naftali Tishby;
1991	1	A Simple Weight Decay Can Improve Generalization IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Anders Krogh; John A. Hertz;
1991	2	Principles Of Risk Minimization For Learning Theory IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	V. Vapnik;
1991	3	Practical Issues In Temporal Difference Learning IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Gerald Tesauro;
1991	4	The Effective Number Of Parameters: An Analysis Of Generalization And Regularization In Nonlinear Learning Systems IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	John E. Moody;
1991	5	Tangent Prop – A Formalism For Specifying Selected Invariances In An Adaptive Network IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	Patrice Simard; Bernard Victorri; Yann LeCun; John Denker;
1991	6	A Contrast Sensitive Silicon Retina With Reciprocal Synapses IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	Kwabena A. Boahen; Andreas G. Andreou;
1991	7	Improving The Performance Of Radial Basis Function Networks By Learning Center Locations IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	Dietrich Wettschereck; Thomas Dietterich;
1991	8	Multi-Digit Recognition Using A Space Displacement Neural Network IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	Ofer Matan; Christopher J. C. Burges; Yann LeCun; John S. Denker;
1991	9	Hierarchies Of Adaptive Experts IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	Michael I. Jordan; Robert A. Jacobs;
1991	10	Active Exploration In Dynamic Environments IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	Sebastian B. Thrun; Knut M�ller;
1991	11	Induction Of Multiscale Temporal Structure IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	Michael C. Mozer;
1991	12	Interpretation Of Artificial Neural Networks: Mapping Knowledge-Based Neural Networks Into Rules IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	Geoffrey Towell; Jude W. Shavlik;
1991	13	Principled Architecture Selection For Neural Networks: Application To Corporate Bond Rating Prediction IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	John Moody; Joachim Utans;
1991	14	Towards Faster Stochastic Gradient Search IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	Christian Darken; John Moody;
1991	15	Structural Risk Minimization For Character Recognition IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	I. Guyon; V. Vapnik; B. Boser; L. Bottou; S. A. Solla;
1990	1	Generalization By Weight-Elimination With Application To Forecasting IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Andreas S. Weigend; David E. Rumelhart; Bernardo A. Huberman;
1990	2	SEXNET: A Neural Network Identifies Sex From Human Faces IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	B.A. Golomb; D.T. Lawrence; T.J. Sejnowski;
1990	3	EMPATH: Face, Emotion, And Gender Recognition Using Holons IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	Garrison W. Cottrell; Janet Metcalfe;
1990	4	Transforming Neural-Net Output Levels To Probability Distributions IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	John S. Denker; Yann LeCun;
1990	5	Spoken Letter Recognition IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	Mark Fanty; Ronald Cole;
1990	6	The Recurrent Cascade-Correlation Architecture IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	Scott E. Fahlman;
1990	7	Note On Learning Rate Schedules For Stochastic Optimization IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	Christian Darken; John E. Moody;
1990	8	Integrated Segmentation And Recognition Of Hand-Printed Numerals IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	James D. Keeler; David E. Rumelhart; Wee Kheng Leow;
1990	9	A Competitive Modular Connectionist Architecture IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	Robert A. Jacobs; Michael I. Jordan;
1990	10	Reinforcement Learning In Markovian And Non-Markovian Environments IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	J�rgen Schmidhuber;
1990	11	Evaluation Of Adaptive Mixtures Of Competing Experts IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	Steven J. Nowlan; Geoffrey E. Hinton;
1990	12	Second Order Properties Of Error Surfaces: Learning Time And Generalization IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View	Yann LeCun; Ido Kanter; Sara A. Solla;
1990	13	Learning Time-varying Concepts IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View	Anthony Kuh; Thomas Petsche; Ronald L. Rivest;
1990	14	Bumptrees For Efficient Function, Constraint And Classification Learning IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	Stephen M. Omohundro;
1990	15	Constructing Hidden Units Using Examples And Queries IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View	Eric B. Baum; Kevin J. Lang;
1989	1	Optimal Brain Damage IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Yann LeCun; John S. Denker; Sara A. Solla;
1989	2	Handwritten Digit Recognition With A Back-Propagation Network IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	YANN LECUN et. al.
1989	3	The Cascade-Correlation Learning Architecture IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Scott E. Fahlman; Christian Lebiere;
1989	4	Reading A Neural Code IF:8 Related Papers Related Patents Related Grants Related Venues Related Experts View	William Bialek; Fred Rieke; Robert R. de Ruyter van Steveninck; David Warland;
1989	5	Training Stochastic Model Recognition Algorithms As Networks Can Lead To Maximum Mutual Information Estimation Of Parameters IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	John S. Bridle;
1989	6	Training Connectionist Networks With Queries And Selective Sampling IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	Les E. Atlas; David A. Cohn; Richard E. Ladner;
1989	7	Maximum Likelihood Competitive Learning IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	Steven J. Nowlan;
1989	8	Higher Order Recurrent Networks And Grammatical Inference IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	C. Lee Giles; Guo-Zheng Sun; Hsing-Hen Chen; Yee-Chun Lee; Dong Chen;
1989	9	Learning To Control An Unstable System With Forward Modeling IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	Michael I. Jordan; Robert A. Jacobs;
1989	10	Synergy Of Clustering Multiple Back Propagation Networks IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	William P. Lincoln; Josef Skrzypek;
1989	11	Designing Application-Specific Neural Networks Using The Genetic Algorithm IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	Steven A. Harp; Tariq Samad; Aloke Guha;
1989	12	An Efficient Implementation Of The Back-propagation Algorithm On The Connection Machine CM-2 IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View	Xiru Zhang; Michael McKenna; Jill P. Mesirov; David L. Waltz;
1989	13	Algorithms For Better Representation And Faster Learning In Radial Basis Function Networks IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View	Avijit Saha; James D. Keeler;
1989	14	Using Local Models To Control Movement IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View	Christopher G. Atkeson;
1989	15	Generalization And Scaling In Reinforcement Learning IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View	David H. Ackley; Michael L. Littman;
1988	1	ALVINN: An Autonomous Land Vehicle In A Neural Network IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Dean A. Pomerleau;
1988	2	What Size Net Gives Valid Generalization? IF:9 Related Papers Related Patents Related Grants Related Venues Related Experts View	Eric B. Baum; David Haussler;
1988	3	Training A 3-Node Neural Network Is NP-Complete IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Avrim Blum; Ronald L. Rivest;
1988	4	Skeletonization: A Technique For Trimming The Fat From A Network Via Relevance Assessment IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Michael C. Mozer; Paul Smolensky;
1988	5	Comparing Biases For Minimal Network Construction With Back-Propagation IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	Stephen Jose Hanson; Lorien Y. Pratt;
1988	6	Winner-Take-All Networks Of O(N) Complexity IF:7 Related Papers Related Patents Related Grants Related Venues Related Experts View	J. Lazzaro; S. Ryckebusch; M.A. Mahowald; C. A. Mead;
1988	7	Links Between Markov Models And Multilayer Perceptrons IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Herv� Bourlard; C. J. Wellekens;
1988	8	A Back-Propagation Algorithm With Optimal Use Of Hidden Units IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	Yves Chauvin;
1988	9	An Application Of The Principle Of Maximum Information Preservation To Linear Systems IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	Ralph Linsker;
1988	10	Consonant Recognition By Modular Construction Of Large Phonemic Time-Delay Neural Networks IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	Alex Waibel;
1988	11	Fast Learning In Multi-Resolution Hierarchies IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	John Moody;
1988	12	Neural Network Recognizer For Hand-Written Zip Code Digits IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	JOHN S. DENKER et. al.
1988	13	Efficient Parallel Learning Algorithms For Neural Networks IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	Alan H. Kramer; Alberto Sangiovanni-Vincentelli;
1988	14	On The K-Winners-Take-All Network IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	E. Majani; Ruth Erlanson; Yaser S. Abu-Mostafa;
1988	15	An Optimality Principle For Unsupervised Learning IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	Terence D. Sanger;
1987	1	How Neural Nets Work IF:6 Related Papers Related Patents Related Grants Related Venues Related Experts View	Alan S. Lapedes; Robert M. Farber;
1987	2	Supervised Learning Of Probability Distributions By Neural Networks IF:5 Related Papers Related Patents Related Grants Related Venues Related Experts View	Eric B. Baum; Frank Wilczek;
1987	3	Neural Net And Traditional Classifiers IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	William Y. Huang; Richard P. Lippmann;
1987	4	Learning Representations By Recirculation IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	Geoffrey E. Hinton; James L. McClelland;
1987	5	Generalization Of Back Propagation To Recurrent And Higher Order Neural Networks IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	Fernando J. Pineda;
1987	6	Constrained Differential Optimization IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	John C. Platt; Alan H. Barr;
1987	7	Static And Dynamic Error Propagation Networks With Application To Speech Coding IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	A. J. Robinson; F. Fallside;
1987	8	On The Power Of Neural Networks For Solving Hard Problems IF:4 Related Papers Related Patents Related Grants Related Venues Related Experts View	Jehoshua Bruck; Joseph W. Goodman;
1987	9	An Optimization Network For Matrix Inversion IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View	Ju-Seog Jang; Soo-Young Lee; Sang-Yung Shin;
1987	10	Encoding Geometric Invariances In Higher-Order Neural Networks IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View	C. Lee Giles; R. D. Griffin; T. Maxwell;
1987	11	MURPHY: A Robot That Learns By Doing IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View	Bartlett W. Mel;
1987	12	An Artificial Neural Network For Spatio-Temporal Bipolar Patterns: Application To Phoneme Classification IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View	Les E. Atlas; Toshiteru Homma; Robert J. Marks II;
1987	13	Stochastic Learning Networks And Their Electronic Implementation IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View	Joshua Alspector; Robert B. Allen; Victor Hu; Srinagesh Satyanarayana;
1987	14	Phasor Neural Networks IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View	Andr� J. Noest;
1987	15	A Dynamical Approach To Temporal Pattern Processing IF:3 Related Papers Related Patents Related Grants Related Venues Related Experts View	W. Scott Stornetta; Tad Hogg; Bernardo A. Huberman;