Search Results for author: Nicolas Vasilache

Found 6 papers, 4 papers with code

Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions

4 code implementations13 Feb 2018 Nicolas Vasilache, Oleksandr Zinenko, Theodoros Theodoridis, Priya Goyal, Zachary DeVito, William S. Moses, Sven Verdoolaege, Andrew Adams, Albert Cohen

Deep learning models with convolutional and recurrent networks are now ubiquitous and analyze massive amounts of audio, image, video, text and graph data, with applications in automatic translation, speech-to-text, scene understanding, ranking user preferences, ad placement, etc.

Scene Understanding

Diagonal Rescaling For Neural Networks

1 code implementation25 May 2017 Jean Lafond, Nicolas Vasilache, Léon Bottou

We define a second-order neural network stochastic gradient training algorithm whose block-diagonal structure effectively amounts to normalizing the unit activations.

Training Language Models Using Target-Propagation

1 code implementation15 Feb 2017 Sam Wiseman, Sumit Chopra, Marc'Aurelio Ranzato, Arthur Szlam, Ruoyu Sun, Soumith Chintala, Nicolas Vasilache

While Truncated Back-Propagation through Time (BPTT) is the most popular approach to training Recurrent Neural Networks (RNNs), it suffers from being inherently sequential (making parallelization difficult) and from truncating gradient flow between distant time-steps.

Learning Visual Features from Large Weakly Supervised Data

no code implementations6 Nov 2015 Armand Joulin, Laurens van der Maaten, Allan Jabri, Nicolas Vasilache

We train convolutional networks on a dataset of 100 million Flickr photos and captions, and show that these networks produce features that perform well in a range of vision problems.

Representation Learning Word Similarity

Fast Convolutional Nets With fbfft: A GPU Performance Evaluation

2 code implementations24 Dec 2014 Nicolas Vasilache, Jeff Johnson, Michael Mathieu, Soumith Chintala, Serkan Piantino, Yann Lecun

We examine the performance profile of Convolutional Neural Network training on the current generation of NVIDIA Graphics Processing Units.

Cannot find the paper you are looking for? You can Submit a new open access paper.