非降阶法研究时变时滞惯性记忆神经网络的无源性和鲁棒无源性。

IF 6 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Neural Networks Pub Date : 2024-12-16 DOI:10.1016/j.neunet.2024.107042

Weizhe Xu , Zihao Li , Song Zhu

{"title":"非降阶法研究时变时滞惯性记忆神经网络的无源性和鲁棒无源性。","authors":"Weizhe Xu , Zihao Li , Song Zhu","doi":"10.1016/j.neunet.2024.107042","DOIUrl":null,"url":null,"abstract":"<div><div>This study examines the concepts of passivity and robust passivity in inertial memristive neural networks (IMNNs) that feature time-varying delays. By using non-smooth analysis and the passivity theorem, algebraic criteria for both passivity and robust passivity are derived by using the non-reduced order method. The proposed criteria, based on the non-reduced order method, effectively reduce the complexity of derivation and computation, thereby simplifying the verification process. Furthermore, asymptotic stability criteria for IMNNs are established in relation to the passivity conditions. In conclusion, two numerical examples are provided to confirm the theoretical results.</div></div>","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"184 ","pages":"Article 107042"},"PeriodicalIF":6.0000,"publicationDate":"2024-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Passivity and robust passivity of inertial memristive neural networks with time-varying delays via non-reduced order method\",\"authors\":\"Weizhe Xu , Zihao Li , Song Zhu\",\"doi\":\"10.1016/j.neunet.2024.107042\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>This study examines the concepts of passivity and robust passivity in inertial memristive neural networks (IMNNs) that feature time-varying delays. By using non-smooth analysis and the passivity theorem, algebraic criteria for both passivity and robust passivity are derived by using the non-reduced order method. The proposed criteria, based on the non-reduced order method, effectively reduce the complexity of derivation and computation, thereby simplifying the verification process. Furthermore, asymptotic stability criteria for IMNNs are established in relation to the passivity conditions. In conclusion, two numerical examples are provided to confirm the theoretical results.</div></div>\",\"PeriodicalId\":49763,\"journal\":{\"name\":\"Neural Networks\",\"volume\":\"184 \",\"pages\":\"Article 107042\"},\"PeriodicalIF\":6.0000,\"publicationDate\":\"2024-12-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Neural Networks\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0893608024009717\",\"RegionNum\":1,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Neural Networks","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0893608024009717","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}

引用次数: 0

摘要

本研究探讨了具有时变延迟的惯性记忆神经网络（imnn）的无源性和鲁棒无源性的概念。利用非光滑分析和无源性定理，利用非降阶方法导出了无源性和鲁棒无源性的代数判据。该准则基于非降阶方法，有效地降低了推导和计算的复杂性，从而简化了验证过程。在此基础上，建立了与无源性条件相关的渐近稳定性判据。最后，给出了两个数值算例来验证理论结果。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Passivity and robust passivity of inertial memristive neural networks with time-varying delays via non-reduced order method

This study examines the concepts of passivity and robust passivity in inertial memristive neural networks (IMNNs) that feature time-varying delays. By using non-smooth analysis and the passivity theorem, algebraic criteria for both passivity and robust passivity are derived by using the non-reduced order method. The proposed criteria, based on the non-reduced order method, effectively reduce the complexity of derivation and computation, thereby simplifying the verification process. Furthermore, asymptotic stability criteria for IMNNs are established in relation to the passivity conditions. In conclusion, two numerical examples are provided to confirm the theoretical results.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Neural Networks 工程技术-计算机：人工智能

CiteScore

13.90

自引率

7.70%

发文量

425

审稿时长

67 days

期刊介绍： Neural Networks is a platform that aims to foster an international community of scholars and practitioners interested in neural networks, deep learning, and other approaches to artificial intelligence and machine learning. Our journal invites submissions covering various aspects of neural networks research, from computational neuroscience and cognitive modeling to mathematical analyses and engineering applications. By providing a forum for interdisciplinary discussions between biology and technology, we aim to encourage the development of biologically-inspired artificial intelligence.