Co-Evolved Spiking Neural Network Ensembles via Marginal Contribution Fitness

2026-06-11

AI Summary

This work addresses the challenge of evolving spiking neural networks (SNNs) in joint topology and parameter spaces as task complexity increases. To overcome this, the authors propose a cooperative game theory–based coevolutionary ensemble framework that defines individual fitness through marginal contributions, seamlessly integrating ensemble formation into the evolutionary process rather than applying it post hoc. This approach effectively enhances population diversity and functional complementarity. Incorporating a differential evaluation mechanism and hardware constraints from the μCaspian neuromorphic platform, the proposed method significantly outperforms both single-network evolution and conventional ensemble strategies across classification, regression, and control tasks. Notably, in control tasks, it achieves a breakthrough by transforming initially ineffective policies into near-optimal performance.

Abstract

Evolutionary optimization of spiking neural networks (SNNs) becomes increasingly difficult as task complexity grows because they must search a combined topology--parameter space that grows super-exponentially with network size. We address this scaling challenge through a co-evolutionary ensemble framework in which a population of candidate SNNs is evolved with fitness defined by each network's marginal contribution to group performance. Grounded in cooperative game theory and difference evaluation functions from multiagent systems, this credit assignment rewards networks that consistently improve ensemble performance and penalizes redundancy, encouraging complementary specialization during evolution rather than relying on post-hoc combination of independently trained networks. We evaluate the approach on classification, regression, and control tasks under $μ$Caspian neuromorphic hardware constraints. Co-evolved ensembles achieve statistically significant improvements over both single-network evolution and post-hoc ensembles across all tasks, with the most pronounced gains in control, where standard evolution fails to discover effective policies and co-evolution enables a qualitative transition to near-optimal performance.

Problem

• spiking neural networks
• evolutionary optimization
• scaling challenge
• topology-parameter space
• task complexity

Innovation

• Co-evolution
• Spiking Neural Networks
• Marginal Contribution Fitness
• Ensemble Learning
• Neuromorphic Computing