Spiking neural networks trained via proxy

TL;DR

This paper introduces a novel proxy-based learning algorithm for training deep spiking neural networks efficiently by leveraging conventional neural networks, achieving high accuracy on benchmark datasets with reduced simulation times.

Contribution

The authors propose a new proxy learning method that couples SNNs with ANNs, enabling effective training of deep SNNs using backpropagation through a shared proxy network.

Findings

Achieved 94.56% accuracy on Fashion-MNIST

Achieved 93.11% accuracy on Cifar10

Outperformed other deep SNN training methods

Abstract

We propose a new learning algorithm to train spiking neural networks (SNN) using conventional artificial neural networks (ANN) as proxy. We couple two SNN and ANN networks, respectively, made of integrate-and-fire (IF) and ReLU neurons with the same network architectures and shared synaptic weights. The forward passes of the two networks are totally independent. By assuming IF neuron with rate-coding as an approximation of ReLU, we backpropagate the error of the SNN in the proxy ANN to update the shared weights, simply by replacing the ANN final output with that of the SNN. We applied the proposed proxy learning to deep convolutional SNNs and evaluated it on two benchmarked datasets of Fashion-MNIST and Cifar10 with 94.56% and 93.11% classification accuracy, respectively. The proposed networks could outperform other deep SNNs trained with tandem learning, surrogate gradient learning, or converted from deep ANNs. Converted SNNs require long simulation times to reach reasonable accuracies while our proxy learning leads to efficient SNNs with much smaller simulation times. The source codes of the proposed method are publicly available at https://github.com/SRKH/ProxyLearning.