An efficient regularized stepwise learning algorithm for training multi-output orthogonal functional basis neural network

Residential College	false
Status	已發表Published
	An efficient regularized stepwise learning algorithm for training multi-output orthogonal functional basis neural network
	Chen C.L.P.3; LeClair S.R.2
	1998-12-01
Source Publication	Intelligent Engineering Systems Through Artificial Neural Networks
Volume	1998 Pages:91-96
Abstract	An efficient learning method for learning multiple output functions using orthogonal functional basis functions is presented in this paper. This method combines subset selection, a well-known technique for generating an efficient and effective neural network structure, and regularization technique. The orthogonal basis is derived from an 'Orthogonal-functional-basis' transformation. This method also reduces the trace of the error covariance matrix. Two nonlinear system modeling examples are used to demonstrate the effectiveness of the learning algorithm.
Keyword	Orthogonal Basis Function Radial Basis Function Supervised Learning
URL	View the original
Language	英語English
Fulltext Access	View Full-Text via Scopus
Document Type	Journal article
Collection	University of Macau
Affiliation	1.IEEE 2.Wright-Patterson AFB 3.Wright State University
Recommended Citation GB/T 7714	Chen C.L.P.,LeClair S.R.. An efficient regularized stepwise learning algorithm for training multi-output orthogonal functional basis neural network[J]. Intelligent Engineering Systems Through Artificial Neural Networks, 1998, 1998, 91-96.
APA	Chen C.L.P.., & LeClair S.R. (1998). An efficient regularized stepwise learning algorithm for training multi-output orthogonal functional basis neural network. Intelligent Engineering Systems Through Artificial Neural Networks, 1998, 91-96.
MLA	Chen C.L.P.,et al."An efficient regularized stepwise learning algorithm for training multi-output orthogonal functional basis neural network".Intelligent Engineering Systems Through Artificial Neural Networks 1998(1998):91-96.

Files in This Item:
There are no files associated with this item.

If you have any objections to this item, please fill out the form below and the administrator will contact you as soon as possible.
Content:
Email：	*
Affiliation No.
Verification Code:	Refresh

Any comments and suggestions are welcomed.
Title:	*
Content:
Email：	*
Verification Code:	Refresh