Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/37725
Title: The further discussions on constrained learning algorithms
Authors: Huang, DS
Keywords: Backpropagation
Feedforward neural nets
Function approximation
Optimisation
Issue Date: 2003
Source: Proceedings of the International Joint Conference on Neural Networks (IJCNN'2003), Portland, Oregon, 20-24 July 2003, p. 1868-1872 How to cite?
Abstract: This paper revisits the constrained learning algorithm (CLA) proposed by Perantonis and Karras (1995), and makes further analyses and discussions on the parameters with the CLAs. Specifically, we investigate the effect of removing the constrained condition of the weight change on the CLAs. It is suggested that for those problems that do not need to do precise computation, the modified CLA is a better choice. Finally, some simulation results are presented to support our claims.
URI: http://hdl.handle.net/10397/37725
ISBN: 0-7803-7898-9
DOI: 10.1109/IJCNN.2003.1223692
Appears in Collections:Conference Paper

Access
View full-text via PolyU eLinks SFX Query
Show full item record

Page view(s)

29
Last Week
4
Last month
Checked on Aug 14, 2017

Google ScholarTM

Check

Altmetric



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.