文献类型：期刊文献

英文题名：Convergence and robustness of bounded recurrent neural networks for solving dynamic Lyapunov equations

作者：Wang, Guancheng[1,2];Hao, Zhihao[1];Zhang, Bob[1];Jin, Long[3]

机构：[1]Univ Macau, Dept Comp & Informat Sci, Taipa 999078, Macau, Peoples R China;[2]Guangdong Ocean Univ, Coll Elect & Informat Engn, Zhanjiang 524088, Peoples R China;[3]Chinese Acad Sci, Chongqing Inst Green & Intelligent Technol, Chongqing Key Lab Big Data & Intelligent Comp, Chongqing 400714, Peoples R China

年份：2022

卷号：588

起止页码：106

外文期刊名：INFORMATION SCIENCES

收录：SCI-EXPANDED(收录号：WOS:000768300300006)、、EI(收录号：20220111413501)、Scopus(收录号：2-s2.0-85121932942)、WOS

基金：This work was supported in part by the University of Macau (File No. MYRG2018-00053-FST), in part by CAS ``Light of West China"Program, in part by the Natural Science Foundation of Chongqing (China) under grant (No. Cstc2020jcyj-zdxmX0028, in part by the National Natural Science Foundation of China (No. 62072121), in part by the "first class" discipline construction platform project in 2019 of Guangdong Ocean University (No. 231419026), in part by the Youth Innovation Project of the Department of Education of Guangdong Province (No. 2020KQNCX026), in part by the Open Research Fund of the Beijing Key Laboratory of Big Data Technology for Food Safety (Project No. BTBD-2021KF05), in part by the Guangdong Basic and Applied Basic Research Foundation(No. 2021A1515011847), in part by the Special Project in Key Fields of Universities in Department of Education of Guangdong Province (No. 2019KZDZX1036), in part by the Guangdong Graduate Education Innovation Project, Graduate Summer School (No. 2020SQXX19), in part by the Guangdong Graduate Education Innovation Project, Graduate Academic Forum (No. 202160), in part by the Key Lab of Digital Signal and Image Processing of Guangdong Province (No. 2019GDDSIPL-01).

语种：英文

外文关键词：Recurrent neural network; dynamic Lyapunov equations; Bounded activation functions; Finite-time convergence; Robustness

外文摘要：Recurrent neural networks have been reported as an effective approach to solve dynamic Lyapunov equations, which widely exist in various application fields. Considering that a bounded activation function should be imposed on recurrent neural networks to solve the dynamic Lyapunov equation in certain situations, a novel bounded recurrent neural network is defined in this paper. Following the definition, several bounded activation func-tions are proposed, and two of them are used to construct the bounded recurrent neural network for demonstration, where one activation function has a finite-time convergence property and the other achieves robustness against noise. Moreover, theoretical analyses provide rigorous and detailed proof of these superior properties. Finally, extensive simula-tion results, including comparative numerical simulations and two application examples, are demonstrated to verify the effectiveness and feasibility of the proposed bounded recur-rent neural network.(c) 2021 Elsevier Inc. All rights reserved.