一种新的动态神经网络在线训练方法

Proceedings of the 2001 IEEE International Conference on Control Applications (CCA'01) (Cat. No.01CH37204) Pub Date : 2001-09-05 DOI:10.1109/CCA.2001.973857

F. Chowdhury

{"title":"一种新的动态神经网络在线训练方法","authors":"F. Chowdhury","doi":"10.1109/CCA.2001.973857","DOIUrl":null,"url":null,"abstract":"A fast, efficient, and novel way of online training of dynamic neural networks is presented in this paper. The method is based on a combination of recursive least-squares and backpropagation; in a large number of cases, backpropagation can be avoided altogether. The proposed method would be suitable for real-time identification, fault detection, and control of uncertain dynamic systems.","PeriodicalId":365390,"journal":{"name":"Proceedings of the 2001 IEEE International Conference on Control Applications (CCA'01) (Cat. No.01CH37204)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2001-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A novel method for online training of dynamic neural networks\",\"authors\":\"F. Chowdhury\",\"doi\":\"10.1109/CCA.2001.973857\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A fast, efficient, and novel way of online training of dynamic neural networks is presented in this paper. The method is based on a combination of recursive least-squares and backpropagation; in a large number of cases, backpropagation can be avoided altogether. The proposed method would be suitable for real-time identification, fault detection, and control of uncertain dynamic systems.\",\"PeriodicalId\":365390,\"journal\":{\"name\":\"Proceedings of the 2001 IEEE International Conference on Control Applications (CCA'01) (Cat. No.01CH37204)\",\"volume\":\"30 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2001-09-05\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 2001 IEEE International Conference on Control Applications (CCA'01) (Cat. No.01CH37204)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CCA.2001.973857\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 2001 IEEE International Conference on Control Applications (CCA'01) (Cat. No.01CH37204)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CCA.2001.973857","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

提出了一种快速、高效、新颖的动态神经网络在线训练方法。该方法基于递推最小二乘和反向传播相结合的方法;在很多情况下，反向传播是完全可以避免的。该方法适用于不确定动态系统的实时识别、故障检测和控制。

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

A novel method for online training of dynamic neural networks

A fast, efficient, and novel way of online training of dynamic neural networks is presented in this paper. The method is based on a combination of recursive least-squares and backpropagation; in a large number of cases, backpropagation can be avoided altogether. The proposed method would be suitable for real-time identification, fault detection, and control of uncertain dynamic systems.

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

Proceedings of the 2001 IEEE International Conference on Control Applications (CCA'01) (Cat. No.01CH37204)

自引率

0.00%

发文量