基于高低阈值的脉冲神经元抗噪学习算法  

A Spiking Neurons noise-resistant learning algorithm with high and low thresholds

作　　者：杨静[1] 徐彦 姜赢 YANG Jing;XU Yan;JIANG Ying(Institute of Advanced Studies in Humanities and Social Sciences,Beijing Normal University,Zhuhai 519087;College of Information Science and Technology,Nanjing Agricultural University,Nanjing 201195,China)

机构地区：[1]北京师范大学人文和社会科学高等研究院,广东珠海519087 [2]南京农业大学信息科技学院,江苏南京201195

出　　处：《计算机工程与科学》2023年第8期1482-1489,共8页Computer Engineering & Science

基　　金：国家自然科学基金(31872847)。

摘　　要：脉冲神经元的动态阈值学习算法在训练神经元的过程中通过改变阈值的大小,可以有效提高神经元的抗噪能力。然而,动态阈值的使用又会降低神经元的学习精度,且在与基于梯度下降的学习算法结合使用时容易导致神经元沉默。基于此,提出了一种改进的基于梯度下降的高低阈值抗噪算法,使用高低阈值来避免神经元的学习精度损失,并在神经元沉默时使用虚拟激发脉冲来继续学习过程,同时使用动态的学习速率来降低高低阈值对学习周期的影响程度。实验结果表明,该算法可以显著提高神经元的抗噪能力,并且能够保证学习精度和收敛速度,适用于基于梯度下降的脉冲神经元学习算法。The dynamic threshold learning algorithm of Spiking neurons can change the size of the threshold during the training process,which can effectively improve the noise resistance of neurons.However,the use of dynamic thresholds can reduce the learning accuracy of neurons and easily cause neuron silence when combining with the gradient-based learning algorithm.To address this issue,an improved gradient-based noise-resistant learning algorithm with high and low thresholds is proposed.This algorithm uses high and low thresholds to avoid loss of learning accuracy and uses virtual excitation pulses to continue the learning process when neurons are silent.At the same time,a dynamic learning rate is used to reduce the impact of high and low thresholds on the learning cycle.The experimental results show that this algorithm can significantly improve the noise resistance of neurons while ensuring learning accuracy and convergence speed.It is well suited for the pulse neuron learning algorithm based on gradient descent.

关 键 词：脉冲神经元 高低阈值 梯度下降 抗噪能力 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]