Demolition and Reinforcement of Memories in Spin-Glass-like Neural Networks

arXiv:2403.02537v1 Announce Type: cross
Abstract: Statistical mechanics has made significant contributions to the study of biological neural systems by modeling them as recurrent networks of interconnected units with adjustable interactions. Several algorithms have been proposed to optimize the neural connections to enable network tasks such as information storage (i.e. associative memory) and learning probability distributions from data (i.e. generative modeling). Among these methods, the Unlearning algorithm, aligned with emerging theories of synaptic plasticity, was introduced by John Hopfield and collaborators. …

abstract algorithms arxiv cond-mat.dis-nn glass information interactions memories memory modeling network networks neural networks reinforcement spin statistical stat.ml storage study systems tasks them type units