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

2025-02-19

arXiv.org

AI Summary

Traditional backpropagation (BP) for training spiking neural networks (SNNs) suffers from computational inefficiency and biological implausibility. To address these limitations, this work introduces the Forward-Forward (FF) algorithm—previously applied to artificial neural networks—into SNN training for the first time, establishing a gradient-free, purely feedforward local learning paradigm. The method employs leaky integrate-and-fire (LIF) neurons within an event-driven training framework, and is rigorously evaluated across static (MNIST, Neuro-MNIST) and neuromorphic spiking (SHD) benchmarks. Results demonstrate that our FF-SNN achieves superior accuracy on MNIST compared to prior FF-based SNNs while using fewer parameters; on SHD, it significantly outperforms most existing SNNs and matches the performance of state-of-the-art BP-trained models. This work establishes a novel, biologically plausible, and hardware-efficient end-to-end spiking learning framework that eliminates backward computation and global error signals.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Deep Learning Algorithms
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

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.

Problem

• Replacing backpropagation in SNNs with Forward-Forward algorithm
• Enhancing computational efficiency and biological plausibility in SNNs
• Achieving competitive accuracy without backpropagation in spiking tasks

Innovation

• Forward-Forward algorithm replaces backpropagation
• Layer-wise localized learning enhances efficiency
• Improved compatibility with neuromorphic hardware