Lingyun Sun, Xuelian Wang, Yuqing Qin, Lei Su, Hao Shen, Jing Wang
{"title":"Passivity Analysis of Markov Jump Inertial Neural Networks Subject to Reaction-Diffusion","authors":"Lingyun Sun, Xuelian Wang, Yuqing Qin, Lei Su, Hao Shen, Jing Wang","doi":"10.1109/DDCLS52934.2021.9455517","DOIUrl":null,"url":null,"abstract":"This paper considers the passivity analysis of inertial neural networks with Markov jump parameters and reaction-diffusion terms. The original second-order differential system, by utilizing a suitable variable transformation, is transformed into a first-order one. The focus is on investigating the passive property of Markov jump reaction-diffusion neural networks. Then, based on Lyapunov stability theory, some sufficient criteria in terms of linear matrix inequality are established to guarantee the desired passive performance of neural networks.","PeriodicalId":325897,"journal":{"name":"2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE 10th Data Driven Control and Learning Systems Conference (DDCLS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/DDCLS52934.2021.9455517","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
This paper considers the passivity analysis of inertial neural networks with Markov jump parameters and reaction-diffusion terms. The original second-order differential system, by utilizing a suitable variable transformation, is transformed into a first-order one. The focus is on investigating the passive property of Markov jump reaction-diffusion neural networks. Then, based on Lyapunov stability theory, some sufficient criteria in terms of linear matrix inequality are established to guarantee the desired passive performance of neural networks.