一种基于牛顿正插值的联想记忆系统

Junsong Wang, Shigang Cui, Xiaoqin Deng, Xingshou Xu, Yundong Li
{"title":"一种基于牛顿正插值的联想记忆系统","authors":"Junsong Wang, Shigang Cui, Xiaoqin Deng, Xingshou Xu, Yundong Li","doi":"10.1142/9789812704313_0047","DOIUrl":null,"url":null,"abstract":"A novel highorder associative memory system based on the Newton's forward Interpolation (NFIAMS) is preposed, which can carry out errorfree approximations to multivariable polynomial functions of arbitrary order. The theory, interpolation algorithm and traning rules of the NFIAMS are discussed in detail. The results of simulating examples indicate that it has more advantadges than CMACtype AMS, such as highprecision of learning, much smaller memory requirement without the datacollision problem and much less computational effort for training and faster convergence rates than that attainable with multilayer BP neural networks.","PeriodicalId":17376,"journal":{"name":"Journal of Tianjin Normal University","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2003-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"A Novel Associative Memory System Based on Newton's Forward Interpolation\",\"authors\":\"Junsong Wang, Shigang Cui, Xiaoqin Deng, Xingshou Xu, Yundong Li\",\"doi\":\"10.1142/9789812704313_0047\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"A novel highorder associative memory system based on the Newton's forward Interpolation (NFIAMS) is preposed, which can carry out errorfree approximations to multivariable polynomial functions of arbitrary order. The theory, interpolation algorithm and traning rules of the NFIAMS are discussed in detail. The results of simulating examples indicate that it has more advantadges than CMACtype AMS, such as highprecision of learning, much smaller memory requirement without the datacollision problem and much less computational effort for training and faster convergence rates than that attainable with multilayer BP neural networks.\",\"PeriodicalId\":17376,\"journal\":{\"name\":\"Journal of Tianjin Normal University\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2003-04-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Tianjin Normal University\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1142/9789812704313_0047\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Tianjin Normal University","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1142/9789812704313_0047","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

提出了一种基于牛顿前向插值(NFI AMS)的高阶联想记忆系统,该系统可以对任意阶的多变量多项式函数进行无误差逼近。详细讨论了NFI AMS的原理、插值算法和训练规则。模拟实例的结果表明,它比CMAC型AMS具有更高的学习精度,更小的内存需求,没有数据冲突问题,训练的计算量更少,收敛速度更快
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
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
A Novel Associative Memory System Based on Newton's Forward Interpolation
A novel highorder associative memory system based on the Newton's forward Interpolation (NFIAMS) is preposed, which can carry out errorfree approximations to multivariable polynomial functions of arbitrary order. The theory, interpolation algorithm and traning rules of the NFIAMS are discussed in detail. The results of simulating examples indicate that it has more advantadges than CMACtype AMS, such as highprecision of learning, much smaller memory requirement without the datacollision problem and much less computational effort for training and faster convergence rates than that attainable with multilayer BP 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
自引率
0.00%
发文量
0
期刊最新文献
On Action Research Individualized Education A Novel Associative Memory System Based on Newton's Forward Interpolation On Thermodynamic Equilibrium Constant
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1