Spiking Neural Networks with Random Network Architecture

TL;DR

This paper introduces RanSNN, a novel spiking neural network architecture inspired by random network design, which reduces training complexity and improves efficiency while maintaining performance and stability.

Contribution

It proposes a new architecture for SNNs that requires training only part of the weights, enabling the use of existing training methods and enhancing efficiency.

Findings

Improved training efficiency over traditional SNN methods

Maintains high performance and stability in benchmark tests

Requires training only a subset of network weights

Abstract

The spiking neural network, known as the third generation neural network, is an important network paradigm. Due to its mode of information propagation that follows biological rationality, the spiking neural network has strong energy efficiency and has advantages in complex high-energy application scenarios. However, unlike the artificial neural network (ANN) which has a mature and unified framework, the SNN models and training methods have not yet been widely unified due to the discontinuous and non-differentiable property of the firing mechanism. Although several algorithms for training spiking neural networks have been proposed in the subsequent development process, some fundamental issues remain unsolved. Inspired by random network design, this work proposes a new architecture for spiking neural networks, RanSNN, where only part of the network weights need training and all the classic training methods can be adopted. Compared with traditional training methods for spiking neural networks, it greatly improves the training efficiency while ensuring the training performance, and also has good versatility and stability as validated by benchmark tests.