NeurIPS 2019
Sun Dec 8th through Sat the 14th, 2019 at Vancouver Convention Center
Paper ID:3824
Title:Updates of Equilibrium Prop Match Gradients of Backprop Through Time in an RNN with Static Input


		
The authors first introduce a discrete-time version of equilibrium propagation (EP). They show the equivalence of EP with backpropagation through time (BPTT). They also apply it to a CNN (first time). They show step-by-step equality under certain conditions. All reviewers agree that the results are original, the quality and clarity of the paper is high, and the results are very significant for the NeurIPS community, in particular to researchers interested in biologically plausible replacements of backpropagation. This paper is a clear accept.