Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagation

TL;DR

This paper introduces a hybrid training method combining conversion and spike-timing dependent backpropagation to efficiently train deep spiking neural networks, significantly reducing training time and the number of time steps needed for accurate inference.

Contribution

The authors propose a novel hybrid training approach that initializes from converted SNNs and applies incremental spike-timing dependent backpropagation, enabling faster convergence and fewer time steps.

Findings

Achieved 65.19% top-1 accuracy on ImageNet with 250 time steps.

Converges in less than 20 epochs on standard datasets.

Reduces training complexity compared to training from scratch.

Abstract

Spiking Neural Networks (SNNs) operate with asynchronous discrete events (or spikes) which can potentially lead to higher energy-efficiency in neuromorphic hardware implementations. Many works have shown that an SNN for inference can be formed by copying the weights from a trained Artificial Neural Network (ANN) and setting the firing threshold for each layer as the maximum input received in that layer. These type of converted SNNs require a large number of time steps to achieve competitive accuracy which diminishes the energy savings. The number of time steps can be reduced by training SNNs with spike-based backpropagation from scratch, but that is computationally expensive and slow. To address these challenges, we present a computationally-efficient training technique for deep SNNs. We propose a hybrid training methodology: 1) take a converted SNN and use its weights and thresholds as an initialization step for spike-based backpropagation, and 2) perform incremental spike-timing dependent backpropagation (STDB) on this carefully initialized network to obtain an SNN that converges within few epochs and requires fewer time steps for input processing. STDB is performed with a novel surrogate gradient function defined using neuron's spike time. The proposed training methodology converges in less than 20 epochs of spike-based backpropagation for most standard image classification datasets, thereby greatly reducing the training complexity compared to training SNNs from scratch. We perform experiments on CIFAR-10, CIFAR-100, and ImageNet datasets for both VGG and ResNet architectures. We achieve top-1 accuracy of 65.19% for ImageNet dataset on SNN with 250 time steps, which is 10X faster compared to converted SNNs with similar accuracy.