2 citations · 4 across the 3 of their papers we have counts for
3 papers
Free Probability for predicting the performance of feed-forward fully connected neural networks
Reda Chhaibi, Tariq Daouda, Ezechiel Kahn
Gradient descent during the learning process of a neural network can be subject to many instabilities. The spectral density of the Jacobian is a key component for analyzing stabili…
Geodesics in fibered latent spaces: A geometric approach to learning correspondences between conditions
Tariq Daouda, Reda Chhaibi, Prudencio Tossou +1
This work introduces a geometric framework and a novel network architecture for creating correspondences between samples of different conditions. Under this formalism, the latent s…
Holographic Neural Architectures
Tariq Daouda, Jeremie Zumer, Claude Perreault +1
Representation learning is at the heart of what makes deep learning effective. In this work, we introduce a new framework for representation learning that we call "Holographic Neur…