Randomized Forward Mode Gradient for Spiking Neural Networks in Scientific Machine Learning

TL;DR

This paper introduces a novel training method for spiking neural networks using randomized forward mode gradients, which improves biological plausibility and hardware efficiency while maintaining competitive accuracy on regression tasks.

Contribution

It proposes a forward-mode gradient approach with weight perturbation for SNNs, offering an alternative to back-propagation that is more compatible with neuromorphic hardware.

Findings

Achieves competitive accuracy on PDE regression tasks

Demonstrates hardware-friendly training method

Offers improved biological plausibility over traditional methods

Abstract

Spiking neural networks (SNNs) represent a promising approach in machine learning, combining the hierarchical learning capabilities of deep neural networks with the energy efficiency of spike-based computations. Traditional end-to-end training of SNNs is often based on back-propagation, where weight updates are derived from gradients computed through the chain rule. However, this method encounters challenges due to its limited biological plausibility and inefficiencies on neuromorphic hardware. In this study, we introduce an alternative training approach for SNNs. Instead of using back-propagation, we leverage weight perturbation methods within a forward-mode gradient framework. Specifically, we perturb the weight matrix with a small noise term and estimate gradients by observing the changes in the network output. Experimental results on regression tasks, including solving various PDEs, show that our approach achieves competitive accuracy, suggesting its suitability for neuromorphic systems and potential hardware compatibility.