# Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks

## TL;DR

This paper introduces a spatio-temporal backpropagation framework for training high-performance spiking neural networks by considering both spatial and temporal information, overcoming non-differentiability issues, and achieving state-of-the-art results.

## Contribution

It proposes a novel STBP training method that integrates spatial and temporal domains and uses an approximated derivative for spike activity, enabling effective gradient descent training of SNNs.

## Key findings

- Achieved top performance on MNIST and N-MNIST datasets.
- Outperformed existing algorithms in multi-layer perceptron training.
- Demonstrated effectiveness on a custom object detection dataset.

## Abstract

Compared with artificial neural networks (ANNs), spiking neural networks (SNNs) are promising to explore the brain-like behaviors since the spikes could encode more spatio-temporal information. Although pre-training from ANN or direct training based on backpropagation (BP) makes the supervised training of SNNs possible, these methods only exploit the networks' spatial domain information which leads to the performance bottleneck and requires many complicated training skills. Another fundamental issue is that the spike activity is naturally non-differentiable which causes great difficulties in training SNNs. To this end, we build an iterative LIF model that is more friendly for gradient descent training. By simultaneously considering the layer-by-layer spatial domain (SD) and the timing-dependent temporal domain (TD) in the training phase, as well as an approximated derivative for the spike activity, we propose a spatio-temporal backpropagation (STBP) training framework without using any complicated technology. We achieve the best performance of multi-layered perceptron (MLP) compared with existing state-of-the-art algorithms over the static MNIST and the dynamic N-MNIST dataset as well as a custom object detection dataset. This work provides a new perspective to explore the high-performance SNNs for future brain-like computing paradigm with rich spatio-temporal dynamics.