Effective methods and framework for energy-based local learning of deep neural networks.

ABSTRACT: From a neuroscience perspective, artificial neural networks are regarded as abstract models of biological neurons, yet they rely on biologically implausible backpropagation for training. Energy-based models represent a class of brain-inspired learning frameworks that adjust system states by minimizing an energy function. Predictive coding (PC), a theoretical model within energy-based models, constructs its energy function from forward prediction errors, with optimization achieved by minimizing local layered errors. Owing to its local plasticity, PC emerges as the most promising alternative to backpropagation. However, PC face gradient explosion and vanishing challenges in deep networks with multiple layers. Gradient explosion occurs when layer-wise prediction errors are excessively large,

SUBMITTER: Chen H 

PROVIDER: S-EPMC12418518 | biostudies-literature | 2025

REPOSITORIES: biostudies-literature