Showing 2023 · cs.LGShow all
2 papers · 2 filters
cs.LG2023
Module-wise Training of Neural Networks via the Minimizing Movement Scheme
Skander Karkar, Ibrahim Ayed, Emmanuel de Bézenac +1
Greedy layer-wise or module-wise training of neural networks is compelling in constrained and on-device settings where memory is limited, as it circumvents a number of problems of…
cs.LG2023
Adversarial Sample Detection Through Neural Network Transport Dynamics
Skander Karkar, Patrick Gallinari, Alain Rakotomamonjy
We propose a detector of adversarial samples that is based on the view of neural networks as discrete dynamic systems. The detector tells clean inputs from abnormal ones by compari…