Taming the chaos gently: a predictive alignment learning rule in recurrent neural networks.

ABSTRACT: Recurrent neural circuits often face inherent complexities in learning and generating their desired outputs, especially when they initially exhibit chaotic spontaneous activity. While the celebrated FORCE learning rule can train chaotic recurrent networks to produce coherent patterns by suppressing chaos, it requires non-local plasticity rules and quick plasticity, raising the question of how synapses adapt on local, biologically plausible timescales to handle potential chaotic dynamics. We propose a novel framework called "predictive alignment", which tames the chaotic recurrent dynamics to generate a variety of patterned activities via a biologically plausible plasticity rule. Unlike most recurrent learning rules, predictive alignment does not aim to directly minimize output error to tra

SUBMITTER: Asabuki T 

PROVIDER: S-EPMC12287340 | biostudies-literature | 2025 Jul

REPOSITORIES: biostudies-literature