# Enabling Spike-based Backpropagation for Training Deep Neural Network Architectures

## TL;DR

This paper introduces a novel approximate derivative method enabling direct spike-based backpropagation for training deep SNNs, overcoming previous limitations and achieving high accuracy on multiple datasets.

## Contribution

It presents the first effective method for training deep convolutional SNNs directly with input spikes using a new approximate derivative approach.

## Key findings

- Achieved state-of-the-art accuracy on MNIST, SVHN, and CIFAR-10 datasets.
- Demonstrated effective inference with sparse event-based computations.
- Enabled training of deep architectures like VGG and Residual networks with spike-based learning.

## Abstract

Spiking Neural Networks (SNNs) have recently emerged as a prominent neural computing paradigm. However, the typical shallow SNN architectures have limited capacity for expressing complex representations while training deep SNNs using input spikes has not been successful so far. Diverse methods have been proposed to get around this issue such as converting off-the-shelf trained deep Artificial Neural Networks (ANNs) to SNNs. However, the ANN-SNN conversion scheme fails to capture the temporal dynamics of a spiking system. On the other hand, it is still a difficult problem to directly train deep SNNs using input spike events due to the discontinuous, non-differentiable nature of the spike generation function. To overcome this problem, we propose an approximate derivative method that accounts for the leaky behavior of LIF neurons. This method enables training deep convolutional SNNs directly (with input spike events) using spike-based backpropagation. Our experiments show the effectiveness of the proposed spike-based learning on deep networks (VGG and Residual architectures) by achieving the best classification accuracies in MNIST, SVHN and CIFAR-10 datasets compared to other SNNs trained with a spike-based learning. Moreover, we analyze sparse event-based computations to demonstrate the efficacy of the proposed SNN training method for inference operation in the spiking domain.