Activity-Dependent Plasticity in Morphogenetically-Grown Recurrent Networks

TL;DR

This study characterizes Hebbian and anti-Hebbian plasticity in morphogenetically grown recurrent networks, showing anti-Hebbian plasticity's superior performance and its evolution-driven discovery, with implications for adaptive neural architectures.

Contribution

It provides a comprehensive analysis of plasticity patterns in morphogenetic neural networks and demonstrates their evolution and functional significance.

Findings

Anti-Hebbian plasticity outperforms Hebbian in competent networks.

Plasticity shifts from fine-tuning to adaptation under non-stationarity.

Evolutionary algorithms discover plasticity patterns matching characterizations.

Abstract

Developmental approaches to neural architecture search grow functional networks from compact genomes through self-organisation, but the resulting networks operate with fixed post-growth weights. We characterise Hebbian and anti-Hebbian plasticity across 50,000 morphogenetically grown recurrent controllers (5M+ configurations on CartPole and Acrobot), then test whether co-evolutionary experiments -- where plasticity parameters are encoded in the genome and evolved alongside the developmental architecture -- recover these patterns independently. Our characterisation reveals that (1) anti-Hebbian plasticity significantly outperforms Hebbian for competent networks (Cohen's d = 0.53-0.64), (2) regret (fraction of oracle improvement lost under the best fixed setting) reaches 52-100%, and (3) plasticity's role shifts from fine-tuning to genuine adaptation under non-stationarity. Co-evolution independently discovers these patterns: on CartPole, 70% of runs evolve anti-Hebbian plasticity (p = 0.043); on Acrobot, evolution finds near-zero eta with mixed signs -- exactly matching the characterisation. A random-RNN control shows that anti-Hebbian dominance is generic to small recurrent networks, but the degree of topology-dependence is developmental-specific: regret is 2-6x higher for morphogenetically grown networks than for random graphs with matched topology statistics.