Benchmarking Spiking Neural Network Learning Methods with Varying Locality

TL;DR

This paper benchmarks various learning methods for Spiking Neural Networks, examining their training similarities, biological plausibility, and robustness, especially when explicit recurrence is added and under adversarial attacks.

Contribution

It compares local learning methods in SNNs, analyzes the effect of explicit recurrence, and evaluates robustness against adversarial attacks.

Findings

Explicit recurrence improves robustness of SNNs.

Local learning methods show a trade-off between biological plausibility and performance.

Adding recurrence enhances SNN robustness against attacks.

Abstract

Spiking Neural Networks (SNNs), providing more realistic neuronal dynamics, have been shown to achieve performance comparable to Artificial Neural Networks (ANNs) in several machine learning tasks. Information is processed as spikes within SNNs in an event-based mechanism that significantly reduces energy consumption. However, training SNNs is challenging due to the non-differentiable nature of the spiking mechanism. Traditional approaches, such as Backpropagation Through Time (BPTT), have shown effectiveness but come with additional computational and memory costs and are biologically implausible. In contrast, recent works propose alternative learning methods with varying degrees of locality, demonstrating success in classification tasks. In this work, we show that these methods share similarities during the training process, while they present a trade-off between biological plausibility and performance. Further, given the implicitly recurrent nature of SNNs, this research investigates the influence of the addition of explicit recurrence to SNNs. We experimentally prove that the addition of explicit recurrent weights enhances the robustness of SNNs. We also investigate the performance of local learning methods under gradient and non-gradient-based adversarial attacks.