Backpropagation-free Spiking Neural Networks with the Forward-Forward Algorithm

TL;DR

This paper introduces a novel training method for Spiking Neural Networks using the Forward-Forward algorithm, which improves efficiency and biological plausibility while achieving competitive accuracy on various datasets.

Contribution

The study presents the first FF-based SNN training framework that enables layer-wise localized learning and demonstrates its effectiveness across multiple static and spiking datasets.

Findings

Outperforms existing FF-based SNNs on static datasets with lighter architectures

Achieves accuracy comparable to backpropagation-trained SNNs on static datasets

Outperforms other SNN models on complex spiking tasks like SHD

Abstract

Spiking Neural Networks (SNNs) offer a biologically inspired computational paradigm that emulates neuronal activity through discrete spike-based processing. Despite their advantages, training SNNs with traditional backpropagation (BP) remains challenging due to computational inefficiencies and a lack of biological plausibility. This study explores the Forward-Forward (FF) algorithm as an alternative learning framework for SNNs. Unlike backpropagation, which relies on forward and backward passes, the FF algorithm employs two forward passes, enabling layer-wise localized learning, enhanced computational efficiency, and improved compatibility with neuromorphic hardware. We introduce an FF-based SNN training framework and evaluate its performance across both non-spiking (MNIST, Fashion-MNIST, Kuzushiji-MNIST) and spiking (Neuro-MNIST, SHD) datasets. Experimental results demonstrate that our model surpasses existing FF-based SNNs on evaluated static datasets with a much lighter architecture while achieving accuracy comparable to state-of-the-art backpropagation-trained SNNs. On more complex spiking tasks such as SHD, our approach outperforms other SNN models and remains competitive with leading backpropagation-trained SNNs. These findings highlight the FF algorithm's potential to advance SNN training methodologies by addressing some key limitations of backpropagation.