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.

翻译：通过自然进化形成的人类大脑复杂而独特的神经网络拓扑结构，使其能够同时执行多种认知功能。生物网络结构的自动进化机制启发我们探索脉冲神经网络（SNNs）的高效架构优化。本文并非采用人工设计的固定架构或分层网络架构搜索（NAS），而是通过融合脑启发的局部模块化结构与全局跨模块连接性来进化SNN架构。在局部层面，受脑区启发的模块由多个具有兴奋性和抑制性连接的神经基序构成；在全局层面，我们进化模块间的自由连接，包括长期跨模块前馈与反馈连接。我们进一步引入基于小样本性能预测器的高效多目标进化算法，使SNN具备高性能、高效率与低能耗特性。在静态数据集（CIFAR10、CIFAR100）和神经形态数据集（CIFAR10-DVS、DVS128-Gesture）上的大量实验表明，我们提出的模型提升了能效，并取得了一致且卓越的性能。这项工作探索了适用于SNN的脑启发神经架构，同时也为理解人脑中生物神经网络的进化机制提供了初步见解。