Axonal Delay As a Short-Term Memory for Feed Forward Deep Spiking Neural Networks

TL;DR

This paper introduces a rectified axonal delay (RAD) module that leverages short-term memory to modulate spike timing in spiking neural networks, enhancing temporal feature learning and achieving state-of-the-art results.

Contribution

It proposes a novel RAD module that integrates axonal delay into supervised learning, focusing on timing adjustments rather than weight changes.

Findings

Achieves state-of-the-art performance on neuromorphic datasets

Uses fewer parameters than existing methods

Improves temporal feature characterization in SNNs

Abstract

The information of spiking neural networks (SNNs) are propagated between the adjacent biological neuron by spikes, which provides a computing paradigm with the promise of simulating the human brain. Recent studies have found that the time delay of neurons plays an important role in the learning process. Therefore, configuring the precise timing of the spike is a promising direction for understanding and improving the transmission process of temporal information in SNNs. However, most of the existing learning methods for spiking neurons are focusing on the adjustment of synaptic weight, while very few research has been working on axonal delay. In this paper, we verify the effectiveness of integrating time delay into supervised learning and propose a module that modulates the axonal delay through short-term memory. To this end, a rectified axonal delay (RAD) module is integrated with the spiking model to align the spike timing and thus improve the characterization learning ability of temporal features. Experiments on three neuromorphic benchmark datasets : NMNIST, DVS Gesture and N-TIDIGITS18 show that the proposed method achieves the state-of-the-art performance while using the fewest parameters.