Soumith Chintala

is this you? claim profile

∙ 2 followers
Facebook

Artificial Intelligence Research Engineer at Facebook AI Research (FAIR) since 2014, Software Engineer at Museami from 2012-2014, Junior Research Scientist at New York University from 2011-2013, Research Intern at Siemens 2011, Client Support at New York University from 2010-2011, Research Scholar at Carnegie Mellon University from 2009-2010.

Featured Co-authors

Kyunghyun Cho
145 publications
Bernhard Schölkopf
118 publications
Yann LeCun
80 publications
Joan Bruna
55 publications
Arthur Szlam
47 publications
Marc'Aurelio Ranzato
39 publications
Koray Kavukcuoglu
38 publications
Douwe Kiela
37 publications
Gabriel Synnaeve
33 publications
Rob Fergus
33 publications
Piotr Dollár
29 publications

PyTorch: An Imperative Style, High-Performance Deep Learning Library

Deep learning frameworks have often focused on either usability or speed...
12/03/2019 ∙ by Adam Paszke, et al. ∙ 90 ∙ share

read it
Generalized Inner Loop Meta-Learning

Many (but not all) approaches self-qualifying as "meta-learning" in deep...
10/03/2019 ∙ by Edward Grefenstette, et al. ∙ 12 ∙ share

read it
Convolutional networks and learning invariant to homogeneous multiplicative scalings

The conventional classification schemes -- notably multinomial logistic ...
06/26/2015 ∙ by Mark Tygert, et al. ∙ 0 ∙ share

read it
Fast Convolutional Nets With fbfft: A GPU Performance Evaluation

We examine the performance profile of Convolutional Neural Network train...
12/24/2014 ∙ by Nicolas Vasilache, et al. ∙ 0 ∙ share

read it
TorchCraft: a Library for Machine Learning Research on Real-Time Strategy Games

We present TorchCraft, a library that enables deep learning research on ...
11/01/2016 ∙ by Gabriel Synnaeve, et al. ∙ 0 ∙ share

read it
Episodic Exploration for Deep Deterministic Policies: An Application to StarCraft Micromanagement Tasks

We consider scenarios from the real-time strategy game StarCraft as new ...
09/10/2016 ∙ by Nicolas Usunier, et al. ∙ 0 ∙ share

read it
Wasserstein GAN

We introduce a new algorithm named WGAN, an alternative to traditional G...
01/26/2017 ∙ by Martin Arjovsky, et al. ∙ 0 ∙ share

read it
MazeBase: A Sandbox for Learning from Games

This paper introduces MazeBase: an environment for simple 2D games, desi...
11/23/2015 ∙ by Sainbayar Sukhbaatar, et al. ∙ 0 ∙ share

read it
Transformation-Based Models of Video Sequences

In this work we propose a simple unsupervised approach for next frame pr...
01/29/2017 ∙ by Joost van Amersfoort, et al. ∙ 0 ∙ share

read it
Semantic Segmentation using Adversarial Networks

Adversarial training has been shown to produce state of the art results ...
11/25/2016 ∙ by Pauline Luc, et al. ∙ 0 ∙ share

read it
Discovering Causal Signals in Images

This paper establishes the existence of observable footprints that revea...
05/26/2016 ∙ by David Lopez-Paz, et al. ∙ 0 ∙ share

read it
A mathematical motivation for complex-valued convolutional networks

A complex-valued convolutional network (convnet) implements the repeated...
03/11/2015 ∙ by Joan Bruna, et al. ∙ 0 ∙ share

read it
A MultiPath Network for Object Detection

The recent COCO object detection dataset presents several new challenges...
04/07/2016 ∙ by Sergey Zagoruyko, et al. ∙ 0 ∙ share

read it
Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks

In this paper we introduce a generative parametric model capable of prod...
06/18/2015 ∙ by Emily Denton, et al. ∙ 0 ∙ share

read it
Pedestrian Detection with Unsupervised Multi-Stage Feature Learning

Pedestrian detection is a problem of considerable practical interest. Ad...
12/01/2012 ∙ by Pierre Sermanet, et al. ∙ 0 ∙ share

read it
Convolutional Neural Networks Applied to House Numbers Digit Classification

We classify digits of real-world house numbers using convolutional neura...
04/18/2012 ∙ by Pierre Sermanet, et al. ∙ 0 ∙ share

read it
Training Language Models Using Target-Propagation

While Truncated Back-Propagation through Time (BPTT) is the most popular...
02/15/2017 ∙ by Sam Wiseman, et al. ∙ 0 ∙ share

read it