%0 Conference Paper
%A Lohoff, Jamie
%A Neftci, Emre
%T Finding new bio-plausible Learning Rules using Deep Reinforcement Learning
%I RWTH Aachen
%M FZJ-2024-01020
%D 2023
%X Gradient-based learning is still the best bet when training spiking neural networks on supervised tasks. Although backpropagation, the state-of-the-art in modern AI, is not bio-plausible, there exists a wide range of approximations with this property that achieve competitive performance, e.g. e-prop[1,2]. We propose a new framework called AlphaGrad that could find more such learning rules by systematically exploring the search space using Deep Reinforcement Learning and methods from Automatic Differentiation(AD).
%B nternational conference on neuromorphic, natural and physical computing
%C 25 Oct 2023 - 27 Oct 2023, Hanover (Germany)
Y2 25 Oct 2023 - 27 Oct 2023
M2 Hanover, Germany
%F PUB:(DE-HGF)24
%9 Poster
%R 10.34734/FZJ-2024-01020
%U https://juser.fz-juelich.de/record/1021872