Recurrent Hamiltonian Echo Learning Enables Biologically Plausible Training of Recurrent Neural Networks
Alice S. Dauphin · Guillaume Pourcel
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.
Chat is not available.
Successful Page Load