A Self-Ensemble Inspired Approach for Effective Training of Binary-Weight Spiking Neural Networks

TL;DR

This paper introduces a novel training method for binary-weight spiking neural networks, inspired by their connection to ensemble models, achieving high accuracy with low latency on ImageNet.

Contribution

It presents a new perspective on SNN training dynamics, linking them to binary neural networks, and proposes the SEI-BWSNN method utilizing shortcuts and knowledge distillation.

Findings

Achieves 82.52% accuracy on ImageNet with 2 time steps

Demonstrates effective training of binary-weight SNNs with low latency

Provides a theoretical analysis connecting SNNs and BNNs

Abstract

Spiking Neural Networks (SNNs) are a promising approach to low-power applications on neuromorphic hardware due to their energy efficiency. However, training SNNs is challenging because of the non-differentiable spike generation function. To address this issue, the commonly used approach is to adopt the backpropagation through time framework, while assigning the gradient of the non-differentiable function with some surrogates. Similarly, Binary Neural Networks (BNNs) also face the non-differentiability problem and rely on approximating gradients. However, the deep relationship between these two fields and how their training techniques can benefit each other has not been systematically researched. Furthermore, training binary-weight SNNs is even more difficult. In this work, we present a novel perspective on the dynamics of SNNs and their close connection to BNNs through an analysis of the backpropagation process. We demonstrate that training a feedforward SNN can be viewed as training a self-ensemble of a binary-activation neural network with noise injection. Drawing from this new understanding of SNN dynamics, we introduce the Self-Ensemble Inspired training method for (Binary-Weight) SNNs (SEI-BWSNN), which achieves high-performance results with low latency even for the case of the 1-bit weights. Specifically, we leverage a structure of multiple shortcuts and a knowledge distillation-based training technique to improve the training of (binary-weight) SNNs. Notably, by binarizing FFN layers in a Transformer architecture, our approach achieves 82.52% accuracy on ImageNet with only 2 time steps, indicating the effectiveness of our methodology and the potential of binary-weight SNNs.