Transition to chaos separates learning regimes and relates to measure of consciousness in recurrent neural networks
bioRxiv Preprint Server May 15, 2024 Dana Mastrovito, Yuhan Helena Liu, Lukasz Kusmierz et al. preprint
Recurrent neural networks exhibit chaotic dynamics when the variance in their connection strengths exceed a critical value. Recent work indicates connection variance also modulates learning strategies; networks learn ”rich” representations when initialized with low coupling and ”lazier”solutions with larger variance. Using Watts-Strogatz networks of varying sparsity, structure, and hidden...