Brain-inspired Evolutionary Architectures for Spiking Neural Networks
This work addresses the need for efficient and high-performing SNN architectures for neuromorphic computing, though it appears incremental by building on existing evolutionary and brain-inspired methods.
The paper tackled the problem of optimizing Spiking Neural Network (SNN) architectures by evolving brain-inspired modular structures and global connections, resulting in improved energy efficiency and consistent performance on static and neuromorphic datasets like CIFAR10 and DVS128-Gesture.
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.