68 citations · 82 across the 6 of their papers we have counts for
6 papers
Training Feature Attribution for Vision Models
Aziz Bacha, Thomas George
Deep neural networks are often considered opaque systems, prompting the need for explainability methods to improve trust and accountability. Existing approaches typically attribute…
Lazy vs hasty: linearization in deep networks impacts learning schedule based on example difficulty
Thomas George, Guillaume Lajoie, Aristide Baratin
Among attempts at giving a theoretical account of the success of deep neural networks, a recent line of work has identified a so-called lazy training regime in which the network ca…
Continual Learning in Deep Networks: an Analysis of the Last Layer
Timothée Lesort, Thomas George, Irina Rish
We study how different output layer parameterizations of a deep neural network affects learning and forgetting in continual learning settings. The following three effects can cause…
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…