{"title":"具有随机波动的脉冲神经网络的收敛稳定性","authors":"Chenhui Zhao, Shan He, Lin Li, Donghui Guo","doi":"10.1109/ICASID.2019.8925103","DOIUrl":null,"url":null,"abstract":"This paper is mainly concerned with the convergence stability of spiking neural networks (SNNs) with stochastic fluctuations. The stochastic fluctuations of spike response model (SRM) are mainly caused by Markovian switching and time delays. The transmission of pulse signals between neurons in this model should be time dependent and its kernel functions should be Lipschitz continuous. Some sufficient criteria are proposed to guarantee the stable convergence of the SRM by using the properties of M-matrix. The stability results have certain reference value for the optimal computation and the design of SNNs with stochastic fluctuations. The numerical illustration is provided to examine the validity of the derived results.","PeriodicalId":422125,"journal":{"name":"2019 IEEE 13th International Conference on Anti-counterfeiting, Security, and Identification (ASID)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Convergence Stability of Spiking Neural Networks with Stochastic Fluctuations\",\"authors\":\"Chenhui Zhao, Shan He, Lin Li, Donghui Guo\",\"doi\":\"10.1109/ICASID.2019.8925103\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper is mainly concerned with the convergence stability of spiking neural networks (SNNs) with stochastic fluctuations. The stochastic fluctuations of spike response model (SRM) are mainly caused by Markovian switching and time delays. The transmission of pulse signals between neurons in this model should be time dependent and its kernel functions should be Lipschitz continuous. Some sufficient criteria are proposed to guarantee the stable convergence of the SRM by using the properties of M-matrix. The stability results have certain reference value for the optimal computation and the design of SNNs with stochastic fluctuations. The numerical illustration is provided to examine the validity of the derived results.\",\"PeriodicalId\":422125,\"journal\":{\"name\":\"2019 IEEE 13th International Conference on Anti-counterfeiting, Security, and Identification (ASID)\",\"volume\":\"97 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2019 IEEE 13th International Conference on Anti-counterfeiting, Security, and Identification (ASID)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICASID.2019.8925103\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 IEEE 13th International Conference on Anti-counterfeiting, Security, and Identification (ASID)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICASID.2019.8925103","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Convergence Stability of Spiking Neural Networks with Stochastic Fluctuations
This paper is mainly concerned with the convergence stability of spiking neural networks (SNNs) with stochastic fluctuations. The stochastic fluctuations of spike response model (SRM) are mainly caused by Markovian switching and time delays. The transmission of pulse signals between neurons in this model should be time dependent and its kernel functions should be Lipschitz continuous. Some sufficient criteria are proposed to guarantee the stable convergence of the SRM by using the properties of M-matrix. The stability results have certain reference value for the optimal computation and the design of SNNs with stochastic fluctuations. The numerical illustration is provided to examine the validity of the derived results.