Contractivity promotes robustness of neural networks
© 2022 EPFL
On Robust Classification using Contractive Hamiltonian Neural ODEs
Contraction theory can improve the robustness of neural ODEs (NODEs).
More precisely, inspired by NODEs with Hamiltonian dynamics, we propose a class of contractive Hamiltonian NODEs (CH-NODEs).
By properly tuning a scalar parameter, CH-NODEs ensure contractivity by design and can be trained using standard backpropagation and gradient descent algorithms.
Moreover, CH-NODEs enjoy built-in guarantees of non-exploding gradients, which ensures a well-posed training process.
For more details and Illustrations read our arXiv report here.