Yann LeCun

Text Understanding from Scratch

Xiang Zhang, Yann LeCun

Comments This technical report is superseded by a paper entitled "Character-level Convolutional Networks for Text Classification", arXiv:1509.01626. It has considerably more experimental results and a rewritten introduction

Super-Resolution with Deep Convolutional Sufficient Statistics

Joan Bruna, Pablo Sprechmann, Yann LeCun

Deep multi-scale video prediction beyond mean square error

Michael Mathieu, Camille Couprie, Yann LeCun

Stacked What-Where Auto-encoders

Junbo Zhao, Michael Mathieu, Ross Goroshin, Yann LeCun

Comments Workshop track - ICLR 2016

Very Deep Multilingual Convolutional Neural Networks for LVCSR

Tom Sercu, Christian Puhrsch, Brian Kingsbury, Yann LeCun

Comments Accepted for publication at ICASSP 2016

Deep learning with Elastic Averaging SGD

Sixin Zhang, Anna Choromanska, Yann LeCun

Comments NIPS2015 camera-ready version

Computing the Stereo Matching Cost with a Convolutional Neural Network

Jure Žbontar, Yann LeCun

Comments Conference on Computer Vision and Pattern Recognition (CVPR), June 2015

High Performance Computer Acoustic Data Accelerator: A New System for Exploring Marine Mammal Acoustics for Big Data Applications

Peter Dugan, John Zollweg, Marian Popescu, Denise Risch, Herve Glotin, Yann LeCun, and Christopher Clark

Comments Seven pages, submitted at International Conference on Machine Learning 2014, Workshop uLearnBio, unsupervised learning for bioacoustic applications

Learning to Linearize Under Uncertainty

Ross Goroshin, Michael Mathieu, Yann LeCun

Comments To appear at NIPS 2015

Unsupervised Learning of Spatiotemporally Coherent Metrics

Ross Goroshin, Joan Bruna, Jonathan Tompson, David Eigen, Yann LeCun

Comments To appear at ICCV2015

Deep Convolutional Networks on Graph-Structured Data

Mikael Henaff, Joan Bruna, Yann LeCun

Efficient Object Localization Using Convolutional Networks

Jonathan Tompson, Ross Goroshin, Arjun Jain, Yann LeCun, Christopher Bregler

Comments 8 pages with 1 page of citations

Fast Training of Convolutional Networks through FFTs

Michael Mathieu, Mikael Henaff, Yann LeCun

Fast approximations to structured sparse coding and applications to object classification

Arthur Szlam, Karol Gregor, Yann LeCun

Scene Parsing with Multiscale Feature Learning, Purity Trees, and Optimal Covers

Clément Farabet, Camille Couprie, Laurent Najman, Yann LeCun

Comments 9 pages, 4 figures - Published in 29th International Conference on Machine Learning (ICML 2012), Jun 2012, Edinburgh, United Kingdom

Audio Source Separation with Discriminative Scattering Networks

Pablo Sprechmann, Joan Bruna, Yann LeCun

Unsupervised Feature Learning from Temporal Data

Ross Goroshin, Joan Bruna, Jonathan Tompson, David Eigen, Yann LeCun

Comments arXiv admin note: substantial text overlap with arXiv:1412.6056

Fast Convolutional Nets With fbfft: A GPU Performance Evaluation

Nicolas Vasilache, Jeff Johnson, Michael Mathieu, Soumith Chintala, Serkan Piantino, Yann LeCun

Comments Camera ready for ICLR2015

Explorations on high dimensional landscapes

Levent Sagun, V. Ugur Guney, Gerard Ben Arous, Yann LeCun

Comments 11 pages, 8 figures, workshop contribution at ICLR 2015

Differentially- and non-differentially-private random decision trees

Mariusz Bojarski, Anna Choromanska, Krzysztof Choromanski, Yann LeCun

The Loss Surfaces of Multilayer Networks

Anna Choromanska, Mikael Henaff, Michael Mathieu, Gérard Ben Arous, Yann LeCun

MoDeep: A Deep Learning Framework Using Motion Features for Human Pose Estimation

Arjun Jain, Jonathan Tompson, Yann LeCun, Christoph Bregler

Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation

Jonathan Tompson, Arjun Jain, Yann LeCun, Christoph Bregler

Spectral Networks and Locally Connected Networks on Graphs

Joan Bruna, Wojciech Zaremba, Arthur Szlam, Yann LeCun

Comments 14 pages

Fast Approximation of Rotations and Hessians matrices

Michael Mathieu, Yann LeCun

Signal Recovery from Pooling Representations

Joan Bruna, Arthur Szlam, Yann LeCun

Comments 17 pages, 3 figures

OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks

Pierre Sermanet, David Eigen, Xiang Zhang, Michael Mathieu, Rob Fergus, Yann LeCun

Understanding Deep Architectures using a Recursive Convolutional Network

David Eigen, Jason Rolfe, Rob Fergus, Yann LeCun

Pedestrian Detection with Unsupervised Multi-Stage Feature Learning

Pierre Sermanet, Koray Kavukcuoglu, Soumith Chintala, Yann LeCun

Comments 12 pages

Adaptive learning rates and parallelization for stochastic, sparse, non-smooth gradients

Tom Schaul, Yann LeCun

Comments Published at the First International Conference on Learning Representations (ICLR-2013). Public reviews are available at http://openreview.net/document/c14f2204-fd66-4d91-bed4-153523694041#c14f2204-fd66-4d91-bed4-153523694041