QQ客服 官方微博 反馈留言

	Robust cost function based parameter learning algorithm for stochastic fuzzy neural network
	Wang junping ; Chen Quanshi
	2010-05-11 ; 2010-05-11
关键词	Theoretical or Mathematical/ filtering theory fuzzy neural nets fuzzy systems learning systems statistical analysis stochastic processes stochastic systems/ robust cost function based parameter learning algorithm stochastic fuzzy neural network traditional least squares cost function noisy input data error variables multiinput single output system robust statistics theory gross error filtering effect robust learning algorithm learning algorithm robust algorithm/ C1230D Neural nets C5290 Neural computing techniques C1140Z Other topics in statistics C1260S Signal processing theory C1340E Self-adjusting control systems
中文摘要	To solve the problem where the parameters of stochastic fuzzy neural network (SFNN) cannot strongly converge to the true values when using traditional least squares cost function with noisy input data, the cost function, which contains the error variables is extended to multi-input single output system. According to robust statistics theory and the directional role of target function, the cost function is mended to treat the gross error and a new robust learning algorithm of SFNN is proposed. The error variables are obtained via learning algorithm to avoid repeated measurement. The simulation results show that the robust algorithm of the SFNN can eliminate the gross error and execute a filtering effect on noisy input.
语种	中文 ; 中文
出版者	Editorial Board J. of Xi'an Jiaotong Univ ; China
内容类型	期刊论文
源URL	[http://hdl.handle.net/123456789/25461]
专题	清华大学
推荐引用方式 GB/T 7714	Wang junping,Chen Quanshi. Robust cost function based parameter learning algorithm for stochastic fuzzy neural network[J],2010, 2010.
APA	Wang junping,&Chen Quanshi.(2010).Robust cost function based parameter learning algorithm for stochastic fuzzy neural network..
MLA	Wang junping,et al."Robust cost function based parameter learning algorithm for stochastic fuzzy neural network".(2010).

个性服务

查看访问统计

相关权益政策

暂无数据

收藏/分享

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。