Neural Architecture Search for Spiking Neural Networks

TL;DR

This paper introduces a novel NAS method to optimize SNN architectures, including feedback connections, leading to state-of-the-art image recognition performance with fewer timesteps.

Contribution

It proposes a NAS approach that searches for optimal SNN architectures, including temporal feedback, without training, improving performance over traditional ANN-like SNNs.

Findings

SNASNet with backward connections outperforms other architectures.

Achieves state-of-the-art results on image benchmarks.

Requires only 5 timesteps for high accuracy.

Abstract

Spiking Neural Networks (SNNs) have gained huge attention as a potential energy-efficient alternative to conventional Artificial Neural Networks (ANNs) due to their inherent high-sparsity activation. However, most prior SNN methods use ANN-like architectures (e.g., VGG-Net or ResNet), which could provide sub-optimal performance for temporal sequence processing of binary information in SNNs. To address this, in this paper, we introduce a novel Neural Architecture Search (NAS) approach for finding better SNN architectures. Inspired by recent NAS approaches that find the optimal architecture from activation patterns at initialization, we select the architecture that can represent diverse spike activation patterns across different data samples without training. Moreover, to further leverage the temporal information among the spikes, we search for feed forward connections as well as backward connections (i.e., temporal feedback connections) between layers. Interestingly, SNASNet found by our search algorithm achieves higher performance with backward connections, demonstrating the importance of designing SNN architecture for suitably using temporal information. We conduct extensive experiments on three image recognition benchmarks where we show that SNASNet achieves state-of-the-art performance with significantly lower timesteps (5 timesteps). Code is available at Github.