计算机应用研究2024，Vol.41Issue(1)：177-182,187,7.DOI:10.19734/j.issn.1001-3695.2023.05.0210
用于双阈值脉冲神经网络的改进自适应阈值算法
Improved adaptive threshold algorithm for double threshold spiking neural network
摘要
Abstract
SNN has gained widespread attention due to its low power consumption and high-speed computing capabilities on neuromorphic chips.The conversion from DNN to SNN is an effective training method for SNN.However,there are approxima-tion errors in the conversion process,leading to significant performance degradation of the converted SNN under short time steps.Through a detailed analysis of the errors in the conversion process,this paper decomposed them into quantization and pruning errors and asymmetric errors,and proposed an improved adaptive threshold algorithm to balance the threshold of SNN.It used the mean square error(MMSE)to achieve a better balance between quantization and pruning errors.Additionally,this algorithm introduced a dual-threshold memory mechanism based on the IF neuron model to effectively address the asymmetric errors.Experimental results demonstrate that the improved algorithm achieves excellent performance on the CIFAR-10,CIFAR-100 datasets,and the MIT-BIH arrhythmia dataset.For the CIFAR-10 dataset,it achieves a high accuracy of 93.22％with only 16 time steps,validating the effectiveness of the algorithm.关键词
脉冲神经网络/高精度转换/双阈值记忆神经元/自适应阈值Key words
spiking neural network/high precision conversion/dual-threshold memory neuron/adaptive threshold分类
信息技术与安全科学引用本文复制引用
王浩杰,刘闯..用于双阈值脉冲神经网络的改进自适应阈值算法[J].计算机应用研究,2024,41(1):177-182,187,7.基金项目
辽宁省自然科学基金资助项目(2023-MS-322) （2023-MS-322）
中国博士后科学基金会资助项目(2021M693858) （2021M693858）
沈阳市中青年科技创新人才支持计划资助项目(RC210400) （RC210400）
辽宁省自然科学基金计划重点项目(20170520364) （20170520364）
