24 citations · 40 across the 11 of their papers we have counts for
11 papers
From Feature Visualization to Visual Circuits: Effect of Adversarial Model Manipulation
Geraldin Nanfack, Michael Eickenberg, Eugene Belilovsky
Understanding the inner working functionality of large-scale deep neural networks is challenging yet crucial in several high-stakes applications. Mechanistic inter- pretability is…
PETRA: Parallel End-to-end Training with Reversible Architectures
Stéphane Rivaud, Louis Fournier, Thomas Pumir +3
Reversible architectures have been shown to be capable of performing on par with their non-reversible architectures, being applied in deep learning for memory savings and generativ…
Channel-Selective Normalization for Label-Shift Robust Test-Time Adaptation
Pedro Vianna, Muawiz Chaudhary, Paria Mehrbod +5
Deep neural networks have useful applications in many different tasks, however their performance can be severely affected by changes in the data distribution. For example, in the b…
Adversarial Attacks on the Interpretation of Neuron Activation Maximization
Geraldin Nanfack, Alexander Fulleringer, Jonathan Marty +2
The internal functional behavior of trained Deep Neural Networks is notoriously difficult to interpret. Activation-maximization approaches are one set of techniques used to interpr…
Can Forward Gradient Match Backpropagation?
Louis Fournier, Stéphane Rivaud, Eugene Belilovsky +2
Forward Gradients - the idea of using directional derivatives in forward differentiation mode - have recently been shown to be utilizable for neural network training while avoiding…
MoMo: Momentum Models for Adaptive Learning Rates
Fabian Schaipp, Ruben Ohana, Michael Eickenberg +2
Training a modern machine learning architecture on a new task requires extensive learning-rate tuning, which comes at a high computational cost. Here we develop new Polyak-type ada…
Local Learning with Neuron Groups
Adeetya Patel, Michael Eickenberg, Eugene Belilovsky
Traditional deep network training methods optimize a monolithic objective function jointly for all the components. This can lead to various inefficiencies in terms of potential par…
Parametric Scattering Networks
Shanel Gauthier, Benjamin Thérien, Laurent Alsène-Racicot +5
The wavelet scattering transform creates geometric invariants and deformation stability. In multiple signal domains, it has been shown to yield more discriminative representations…
Decoupled Greedy Learning of CNNs for Synchronous and Asynchronous Distributed Learning
Eugene Belilovsky, Louis Leconte, Lucas Caccia +2
A commonly cited inefficiency of neural network training using back-propagation is the update locking problem: each layer must wait for the signal to propagate through the full net…
Decoupled Greedy Learning of CNNs
Eugene Belilovsky, Michael Eickenberg, Edouard Oyallon
A commonly cited inefficiency of neural network training by back-propagation is the update locking problem: each layer must wait for the signal to propagate through the full networ…
Greedy Layerwise Learning Can Scale to ImageNet
Eugene Belilovsky, Michael Eickenberg, Edouard Oyallon
Shallow supervised 1-hidden layer neural networks have a number of favorable properties that make them easier to interpret, analyze, and optimize than their deep counterparts, but…