计算机科学 ›› 2023, Vol. 50 ›› Issue (8): 221-225.doi: 10.11896/jsjkx.220700181
马韦伟1, 郑勤红2, 刘珊珊3
MA Weiwei1, ZHENG Qinhong2, LIU Shanshan3
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。
中图分类号:
| [1]SONG D,LU K,DAI X F.Research on Mail Classification Algorithm Based on Improved Convolutional Neural Network[J].Journal of Chongqing Technology and Business University(Na-tural Science Edition),2022,39(3):20-25. [2]ZHANG X F,WANG Z Q,TANG Y L.Helmet Detection Based on YOLO-CDF Neural Network[J].Journal of Chongqing Technology and Business University(Natural Science Edition),2022,39(4):32-41. [3]ZHUANG Z J,FANG Y,LEI J C,et al.Research on impulse neural network based on STDP rules[J].Computer Enginee-ring,2020,46(9):83-88,94. [4]WANG Q H,WANG L N,XU S.Research and application of pulse neural network model fused with LSTM structure[J].Computer Application Research,2021,38(5):1381-1386. [5]AUGE D,HILLE J,MUELLER E,et al.A survey of encoding techniques for signal processing in spiking neural networks[J].Neural Processing Letters,2021,53(6):4693-4710. [6]WEI Q M,LI Y B,YING Y L.Network security situation prediction based on Dempster-Shafer evidence theory and recurrent neural network [J].Journal of University of Jinan(Science and Technology),2020,34(3):238-246. [7]XIAO M,MENG Q,ZHANG Z,et al.Training feedback spiking neural networks by implicit differentiation on the equilibrium state[J].Advances in Neural Information Processing Systems,2021,34:14516-14528. [8]FANG W,YU Z,CHEN Y,et al.Deep residual learning in spiking neural networks[J].Advances in Neural Information Processing Systems,2021,34:21056-21069. [9]LOBO J L,DEL SER J,BIFET A,et al.Spiking neural networks and online learning:An overview and perspectives[J].Neural Networks,2020,121:88-100. [10]TAVANAEI A,GHODRATI M,KHERADPISHEH S R,et al.Deep learning in spiking neural networks[J].Neural Networks,2019,111:47-63. [11]AWADALLAH M A,AL-BETAR M A,BOLAJI A L,et al.Natural selection methods for artificial bee colony with new versions of onlooker bee[J].Soft Computing,2019,23(15):6455-6494. [12]LI J Q,SONG M X,WANG L,et al.Hybrid Artificial Bee Colony Algorithm for a Parallel Batching Distributed Flow-Shop Problem With Deteriorating Jobs[J].IEEE Transactions on Cybernetics,2020,50(6):2425-2439. [13]FOROUZANDEH S,BERAHMAND K,NASIRI E,et al.AHotel Recommender System for Tourists Using the Artificial Bee Colony Algorithm and Fuzzy TOPSIS Model:A Case Study of TripAdvisor[J].International Journal of Information Technology and Decision Making,2021,20(1):399-429. [14]LIU J,GUO Z W,SUN Z W,et al.Research on fast multi label support vector machine classification algorithm using divide and conquer strategy[J].Journal of Ocean University of China(Na-tural Science Edition),2020,50(12):160-166. [15]LIU J Z,DUAN L.Network security text multi label classification method based on Albert textcnn[J].Naval Electronic Engineering,2022,42(3):114-118,170. [16]YANG M H,CHEN L,LIU H,et al.Multi label remote sensing image classification based on graph convolution network[J].Computer Application Research,2021,38(11):3439-3445. |
|
||
首页