Equilibrium Propagation for Complete Directed Neural Networks
Machine Learning
2020-06-18 v2 Neural and Evolutionary Computing
Machine Learning
Abstract
Artificial neural networks, one of the most successful approaches to supervised learning, were originally inspired by their biological counterparts. However, the most successful learning algorithm for artificial neural networks, backpropagation, is considered biologically implausible. We contribute to the topic of biologically plausible neuronal learning by building upon and extending the equilibrium propagation learning framework. Specifically, we introduce: a new neuronal dynamics and learning rule for arbitrary network architectures; a sparsity-inducing method able to prune irrelevant connections; a dynamical-systems characterization of the models, using Lyapunov theory.
Cite
@article{arxiv.2006.08798,
title = {Equilibrium Propagation for Complete Directed Neural Networks},
author = {Matilde Tristany Farinha and Sérgio Pequito and Pedro A. Santos and Mário A. T. Figueiredo},
journal= {arXiv preprint arXiv:2006.08798},
year = {2020}
}
Comments
6 pages, 6 images, accepted for ESANN 2020