具有长程反馈的神经网络:稳定动力学设计

Proceedings Eighth IEEE International Conference on Tools with Artificial Intelligence Pub Date : 1996-11-16 DOI:10.1109/TAI.1996.560462

R. Braham

{"title":"具有长程反馈的神经网络:稳定动力学设计","authors":"R. Braham","doi":"10.1109/TAI.1996.560462","DOIUrl":null,"url":null,"abstract":"Feedback in neural networks is essential. Without it, true dynamics would be lacking. For this reason, many well known models include feedback connections (e.g. Hopfield, ART, neocognitron). Neural networks with feedback are, however, likely to be unstable if not carefully designed. In this paper, we show how to incorporate long-range feedback in a class of dynamically stable nonlinear neural networks.","PeriodicalId":209171,"journal":{"name":"Proceedings Eighth IEEE International Conference on Tools with Artificial Intelligence","volume":"11 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1996-11-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Neural networks with long-range feedback: design for stable dynamics\",\"authors\":\"R. Braham\",\"doi\":\"10.1109/TAI.1996.560462\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Feedback in neural networks is essential. Without it, true dynamics would be lacking. For this reason, many well known models include feedback connections (e.g. Hopfield, ART, neocognitron). Neural networks with feedback are, however, likely to be unstable if not carefully designed. In this paper, we show how to incorporate long-range feedback in a class of dynamically stable nonlinear neural networks.\",\"PeriodicalId\":209171,\"journal\":{\"name\":\"Proceedings Eighth IEEE International Conference on Tools with Artificial Intelligence\",\"volume\":\"11 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"1996-11-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings Eighth IEEE International Conference on Tools with Artificial Intelligence\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/TAI.1996.560462\",\"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 Eighth IEEE International Conference on Tools with Artificial Intelligence","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/TAI.1996.560462","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 1

摘要

神经网络中的反馈是必不可少的。没有它，就没有真正的动力。由于这个原因，许多著名的模型包括反馈连接(例如Hopfield, ART, neocognitron)。然而，如果设计不当，带有反馈的神经网络很可能不稳定。在本文中，我们展示了如何在一类动态稳定的非线性神经网络中加入远程反馈。

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

微信好友朋友圈 QQ好友复制链接

本刊更多论文

Neural networks with long-range feedback: design for stable dynamics

Feedback in neural networks is essential. Without it, true dynamics would be lacking. For this reason, many well known models include feedback connections (e.g. Hopfield, ART, neocognitron). Neural networks with feedback are, however, likely to be unstable if not carefully designed. In this paper, we show how to incorporate long-range feedback in a class of dynamically stable nonlinear neural networks.

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 Eighth IEEE International Conference on Tools with Artificial Intelligence

自引率

0.00%

发文量

期刊最新文献

AI tools in scheduling problem solving: a solver based on a "well-behaved" restriction of TCSPs A deliberative and reactive diagnosis agent based on logic programming Subdefinite models as a variety of constraint programming Oz Scheduler: a workbench for scheduling problems Automatic scale selection as a pre-processing stage to interpreting real-world data