基于蜂群优化的Spiking神经网络模型研究与评估  

Study and Evaluation of Spiking Neural Network Model Based on Bee Colony Optimization

作　　者：马韦伟 郑勤红[2] 刘珊珊 MA Weiwei;ZHENG Qinhong;LIU Shanshan(Faculty of Education,Yunnan Normal University,Kunming 650500,China;College of Physics and Electronic Information,Yunnan Normal University,Kunming 650500,China;School of Technology,Asia-pacific University of Science and Technology,Kuala Lumpur 56000,Malaysia)

机构地区：[1]云南师范大学教育学部,昆明650500 [2]云南师范大学物理与电子信息学院,昆明650500 [3]亚太科技大学科技学院,吉隆坡56000

出　　处：《计算机科学》2023年第8期221-225,共5页Computer Science

基　　金：国家自然科学基金(61961044);教育部人文社会科学研究基金项目(20XJA880008);云南省教育厅科学研究基金项目(2021Y512)。

摘　　要：为提高Spiking神经网络的训练能力,以多标签分类问题作为研究切入点,采用蜂群算法进行模型优化。基于Spiking理念的神经网络模型有多种,文中选择概率Spiking神经网络(Probabilistic Spiking Neural Network,PSNN)进行多标签分类。首先,建立概率Spiking神经网络分类模型,通过点火时间序列进行编码,触发脉冲响应实现数据传递;然后,利用Spiking神经网络的权重、动态阈值、遗忘参数等构建蜂群,并以多标签分类准确率作为人工蜂群(Artificial Bee Colony,ABC)算法的适应度函数,从而通过不断更新蜂群个体适应度值来获得最优个体;最后,以最优参数完成概率Spiking神经网络的多标签分类。实验结果表明,通过合理设置蜂群个体规模及蜜源搜索范围,ABC-PSNN算法能够获得较高的多标签分类准确率。相比其他Spiking神经网络模型和常用多标签分类算法,ABC-PSNN算法具备更高的分类准确率和稳定性。In order to improve the training ability of Spiking neural network,this paper takes multi-label classification problem as the research breakthrough point and adopts bee colony algorithm to optimize the model.There are many neural network models based on the concept of Spiking.Probabilistic Spiking neural network(PSNN)is selected for multi-label classification.Firstly,a probabilistic Spiking neural network classification model is established.The ignition time sequence is coded,and the pulse res-ponse is triggered to realize data transmission.Then,the weight,dynamic threshold and forgetting parameters of Spiking neural network are used to construct bee colony,and the accuracy of multi-label classification is used as the fitness function of artificial bee colony(ABC)algorithm,so that the optimal individual can be obtained by constantly updating the fitness value of individual bee colony.Finally,the multi-label classification of probabilistic Spiking neural network is completed with the optimal parameters.Experimental results show that ABC-PSNN algorithm can achieve high multi-label classification accuracy by reasonably setting the individual size of bee colony and honey source search range.Compared with other Spiking neural network models and commonly used multi-label classification algorithms,ABC-PSNN algorithm has higher classification accuracy and stability.

关 键 词：SPIKING神经网络 概率Spiking神经网络 蜂群算法 多标签分类 脉冲响应 

分 类 号：TP3-05[自动化与计算机技术—计算机科学与技术]