基于脉冲神经元膜电位增量的数据分布统计量及批归一化

打开文本图片集

关键词：脉冲神经网络；批归一化；脉冲时间依赖性；脉冲神经网络训练算法中图分类号：TP183 文献标志码：A 文章编号：1001-3695（2025）08-013-2341-07doi：10.19734/j.issn.1001-3695.2024.12.0529

Data distribution statistics and batch normalization based on membrane potential increments of spiking neurons

LiWeiqi¹，ChenYunhual†，ChenPinghua1，Zhu Chunjia² （1.SchoolofComputerSience&Tchologyuangdong UniersityfTchologyuangzhou5o，hina;2.ChinaSibldingR search&DesignCenter，NeijiangSichuan641199，China）

Abstract：SNN has garnered significant atention due to theirlow power consumptionand high-speedcomputation，stemming fromtheiravoidanceof multiplicationoperations.However，substantial challnges remainin theareas of training algorithms， hyperparameter tuning，andarchitecture designforSNN.Adressng the limitations of existing BNmethods inefectively handling temporal dependencies，thispaperanalyzed thepropagationof membrane potential incrementsacrosstimesteps.The proposed method computed the spatio-temporal accumulationof membrane potential increments step-by-stepas statistical measuresfornormalizingdataateachtimestep.Furthermore，itintroducedanexponentiallweighted moving average tocompute thespatio-temporalaccumulationofmembranepotentialincrements，foringaspatio-temporalatenuationcumulativebatch normalization（STBN）method.Experimentalresultsonthe CIFAR-10，CIFAR-10O，and CIFAR10-DVS datasets demonstrate that the proposed method significantly improves network clasificationaccuracyandreduces latency.Notably，onthe CIFAR100 dataset， the method achieves an accuracy of 76.30% using only two time steps， representing a 3.43% improvement over the previous best algorithm for similar models.

Key words：spiking neural network（SNN）；batch normalization（BN）；temporal dependencies inspiking；training algo rithmsfor spikingneural network

0 引言

由脑科学启发设计出的脉冲神经网络（SNN）[1～3]作为第三代人工神经网络，有着更好的生物解释性。（剩余17494字）