Equilibrium Propagation for Complete Directed Neural Networks
This work addresses biologically plausible learning for neural networks, which is an incremental advancement in the field.
The paper tackled the problem of biologically implausible learning algorithms like backpropagation by extending the equilibrium propagation framework, introducing a new neuronal dynamics and learning rule for arbitrary architectures, a sparsity-inducing pruning method, and a dynamical-systems characterization using Lyapunov theory.
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.