A modified Elman neural network with a new learning rate scheme

Ren, G; Cao, Y; Wen, S; Huang, T; Zeng, Z

A modified Elman neural network with a new learning rate scheme

Ren, G Cao, Y Wen, S

Huang, T Zeng, Z

Permalink

Publisher:: ELSEVIER SCIENCE BV
Publication Type:: Journal Article
Citation:: Neurocomputing, 2018, 286, pp. 11-18
Issue Date:: 2018-04-19

Closed Access

	Filename	Description	Size
	1-s2.0-S0925231218300717-main.pdf	Published version	950.15 kB		View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Ren, G
dc.contributor.author	Cao, Y
dc.contributor.author	Wen, S https://orcid.org/0000-0001-8077-7001
dc.contributor.author	Huang, T
dc.contributor.author	Zeng, Z
dc.date.accessioned	2022-09-04T07:24:45Z
dc.date.available	2022-09-04T07:24:45Z
dc.date.issued	2018-04-19
dc.identifier.citation	Neurocomputing, 2018, 286, pp. 11-18
dc.identifier.issn	0925-2312
dc.identifier.issn	1872-8286
dc.identifier.uri	http://hdl.handle.net/10453/161312
dc.description.abstract	Elman neural network (ENN) is one of recurrent neural networks (RNNs). Comparing to traditional neural networks, ENN has additional inputs from the hidden layer, which forms a new layer–the context layer. So the standard back-propagation (BP) algorithm used in ENN is called Elman back-propagation algorithm (EBP). ENN can be applied to solve prediction problems of discrete time sequence. However, the EBP algorithm suffers from low convergence speed and poor generalization performance. To solve this problem, a new learning rate scheme is proposed, the convergence of new proposed scheme is proved. Furthermore, the contrast experiment is utilized to demonstrate the effectiveness of the proposed scheme from the aspects of convergence speed and consumption time with some popular schemes such as the original ENN, and PSO–ENN which uses PSO algorithm to search the best structure of ENN. The experience shows that the modified method proposed in this paper works best.
dc.language	English
dc.publisher	ELSEVIER SCIENCE BV
dc.relation	National Natural Science Foundation of China61673187
dc.relation.ispartof	Neurocomputing
dc.relation.isbasedon	10.1016/j.neucom.2018.01.046
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	08 Information and Computing Sciences, 09 Engineering, 17 Psychology and Cognitive Sciences
dc.subject.classification	Artificial Intelligence & Image Processing
dc.title	A modified Elman neural network with a new learning rate scheme
dc.type	Journal Article
utslib.citation.volume	286
utslib.for	08 Information and Computing Sciences
utslib.for	09 Engineering
utslib.for	17 Psychology and Cognitive Sciences
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - AAII - Australian Artificial Intelligence Institute
utslib.copyright.status	closed_access	*
dc.date.updated	2022-09-04T07:24:44Z
pubs.publication-status	Published
pubs.volume	286

Abstract:

Elman neural network (ENN) is one of recurrent neural networks (RNNs). Comparing to traditional neural networks, ENN has additional inputs from the hidden layer, which forms a new layer–the context layer. So the standard back-propagation (BP) algorithm used in ENN is called Elman back-propagation algorithm (EBP). ENN can be applied to solve prediction problems of discrete time sequence. However, the EBP algorithm suffers from low convergence speed and poor generalization performance. To solve this problem, a new learning rate scheme is proposed, the convergence of new proposed scheme is proved. Furthermore, the contrast experiment is utilized to demonstrate the effectiveness of the proposed scheme from the aspects of convergence speed and consumption time with some popular schemes such as the original ENN, and PSO–ENN which uses PSO algorithm to search the best structure of ENN. The experience shows that the modified method proposed in this paper works best.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/161312