Poster
in
Affinity Workshop: Women in Machine Learning

Recurrent Hamiltonian Echo Learning Enables Biologically Plausible Training of Recurrent Neural Networks

Alice S. Dauphin · Guillaume Pourcel

Project Page

Abstract

We combined RHEL, a recently introduced training algorithm, with a Hopfield-inspired Hamiltonian RNN, obtaining a local contrastive Hebbian rule that enables biologically plausible temporal credit assignment and matches BPTT-level performance.