Time-independent Spiking Neuron via Membrane Potential Estimation for Efficient Spiking Neural Networks

TL;DR

This paper introduces MPE-PSN, a parallel computation method for spiking neurons that significantly improves efficiency and accuracy in SNNs by enabling parallel membrane potential updates, especially beneficial at high neuron densities.

Contribution

We propose MPE-PSN, a novel parallel computation approach for spiking neurons that maintains dynamic properties while enhancing efficiency and accuracy in SNNs.

Findings

Achieves state-of-the-art accuracy on neuromorphic datasets.

Significantly improves computational efficiency at high neuron densities.

Enables effective parallel processing of membrane potentials.

Abstract

The computational inefficiency of spiking neural networks (SNNs) is primarily due to the sequential updates of membrane potential, which becomes more pronounced during extended encoding periods compared to artificial neural networks (ANNs). This highlights the need to parallelize SNN computations effectively to leverage available hardware parallelism. To address this, we propose Membrane Potential Estimation Parallel Spiking Neurons (MPE-PSN), a parallel computation method for spiking neurons that enhances computational efficiency by enabling parallel processing while preserving the intrinsic dynamic characteristics of SNNs. Our approach exhibits promise for enhancing computational efficiency, particularly under conditions of elevated neuron density. Empirical experiments demonstrate that our method achieves state-of-the-art (SOTA) accuracy and efficiency on neuromorphic datasets. Codes are available at~\url{https://github.com/chrazqee/MPE-PSN}. \end{abstract}