Brain-inspired Evolutionary Architectures for Spiking Neural Networks

TL;DR

This paper introduces a brain-inspired evolutionary approach to optimize Spiking Neural Network architectures, incorporating local neural motifs and global connectivity, resulting in high performance and energy efficiency on various datasets.

Contribution

It proposes a novel evolutionary framework for SNN architecture design inspired by brain structures, using a multi-objective algorithm with a performance predictor.

Findings

Achieves high accuracy on CIFAR10 and CIFAR100 datasets.

Demonstrates significant energy efficiency improvements.

Provides insights into biological neural network evolution.

Abstract

The complex and unique neural network topology of the human brain formed through natural evolution enables it to perform multiple cognitive functions simultaneously. Automated evolutionary mechanisms of biological network structure inspire us to explore efficient architectural optimization for Spiking Neural Networks (SNNs). Instead of manually designed fixed architectures or hierarchical Network Architecture Search (NAS), this paper evolves SNNs architecture by incorporating brain-inspired local modular structure and global cross-module connectivity. Locally, the brain region-inspired module consists of multiple neural motifs with excitatory and inhibitory connections; Globally, we evolve free connections among modules, including long-term cross-module feedforward and feedback connections. We further introduce an efficient multi-objective evolutionary algorithm based on a few-shot performance predictor, endowing SNNs with high performance, efficiency and low energy consumption. Extensive experiments on static datasets (CIFAR10, CIFAR100) and neuromorphic datasets (CIFAR10-DVS, DVS128-Gesture) demonstrate that our proposed model boosts energy efficiency, archiving consistent and remarkable performance. This work explores brain-inspired neural architectures suitable for SNNs and also provides preliminary insights into the evolutionary mechanisms of biological neural networks in the human brain.