复杂系统神经网络模型在线学习算法的收敛性

2013 IEEE 2nd International Conference Actual Problems of Unmanned Air Vehicles Developments Proceedings (APUAVD) Pub Date : 2013-10-01 DOI:10.1109/APUAVD.2013.6705293

V. Azarskov, S. Nikolaienko, L. Zhiteckii

{"title":"复杂系统神经网络模型在线学习算法的收敛性","authors":"V. Azarskov, S. Nikolaienko, L. Zhiteckii","doi":"10.1109/APUAVD.2013.6705293","DOIUrl":null,"url":null,"abstract":"Asymptotic behavior of the online gradient algorithm with a constant step size employed for learning in neural network models of nonlinear systems having hidden layer are studied. The sufficient conditions guaranteeing the convergence of this algorithm in the random environment are established.","PeriodicalId":400843,"journal":{"name":"2013 IEEE 2nd International Conference Actual Problems of Unmanned Air Vehicles Developments Proceedings (APUAVD)","volume":"221 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Convergence properties of an online learning algorithm in neural network models of complex systems\",\"authors\":\"V. Azarskov, S. Nikolaienko, L. Zhiteckii\",\"doi\":\"10.1109/APUAVD.2013.6705293\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Asymptotic behavior of the online gradient algorithm with a constant step size employed for learning in neural network models of nonlinear systems having hidden layer are studied. The sufficient conditions guaranteeing the convergence of this algorithm in the random environment are established.\",\"PeriodicalId\":400843,\"journal\":{\"name\":\"2013 IEEE 2nd International Conference Actual Problems of Unmanned Air Vehicles Developments Proceedings (APUAVD)\",\"volume\":\"221 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2013-10-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2013 IEEE 2nd International Conference Actual Problems of Unmanned Air Vehicles Developments Proceedings (APUAVD)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/APUAVD.2013.6705293\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 IEEE 2nd International Conference Actual Problems of Unmanned Air Vehicles Developments Proceedings (APUAVD)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/APUAVD.2013.6705293","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

摘要

研究了用于具有隐层非线性系统的神经网络模型学习的恒步长在线梯度算法的渐近行为。给出了保证该算法在随机环境下收敛的充分条件。

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

Convergence properties of an online learning algorithm in neural network models of complex systems

Asymptotic behavior of the online gradient algorithm with a constant step size employed for learning in neural network models of nonlinear systems having hidden layer are studied. The sufficient conditions guaranteeing the convergence of this algorithm in the random environment are established.

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

2013 IEEE 2nd International Conference Actual Problems of Unmanned Air Vehicles Developments Proceedings (APUAVD)

自引率

0.00%

发文量