71 citations · 206 across the 5 of their papers we have counts for
7 papers
Implicit Regularization via Neural Feature Alignment
Aristide Baratin, Thomas George, César Laurent +4
We approach the problem of implicit regularization in deep learning from a geometrical viewpoint. We highlight a regularization effect induced by a dynamical alignment of the neura…
Revisiting Loss Modelling for Unstructured Pruning
César Laurent, Camille Ballas, Thomas George +2
By removing parameters from deep neural networks, unstructured pruning methods aim at cutting down memory footprint and computational cost, while maintaining prediction accuracy. I…
Fast Approximate Natural Gradient Descent in a Kronecker-factored Eigenbasis
Thomas George, César Laurent, Xavier Bouthillier +2
Optimization algorithms that leverage gradient covariance information, such as variants of natural gradient descent (Amari, 1998), offer the prospect of yielding more effective des…
Towards End-to-End Speech Recognition with Deep Convolutional Neural Networks
Ying Zhang, Mohammad Pezeshki, Philemon Brakel +3
Convolutional Neural Networks (CNNs) are effective models for reducing spectral variations and modeling spectral correlations in acoustic features for automatic speech recognition…
Theano: A Python framework for fast computation of mathematical expressions
The Theano Development Team, Rami Al-Rfou, Guillaume Alain +110
Theano is a Python library that allows to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. Since its introduction, it has bee…
Recurrent Batch Normalization
Tim Cooijmans, Nicolas Ballas, César Laurent +2
We propose a reparameterization of LSTM that brings the benefits of batch normalization to recurrent neural networks. Whereas previous works only apply batch normalization to the i…
Batch Normalized Recurrent Neural Networks
César Laurent, Gabriel Pereyra, Philémon Brakel +2
Recurrent Neural Networks (RNNs) are powerful models for sequential data that have the potential to learn long-term dependencies. However, they are computationally expensive to tra…