Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/5394
Title: Formation and dynamics of modules in a dual-tasking multilayer feed-forward neural network
Authors: Lam, CH 
Shin, FG
Keywords: Brain models
Feedforward neural nets
Function approximation
Subroutines
Issue Date: Sep-1998
Publisher: American Physical Society
Source: Physical review E, statistical, nonlinear, and soft matter physics, Sept. 1998, v. 58, no. 3, p. 3673-3677 How to cite?
Journal: Physical review E, statistical, nonlinear, and soft matter physics 
Abstract: We study a feed-forward neural network for two independent function approximation tasks. Upon training, two modules are automatically formed in the hidden layers, each handling one of the tasks predominantly. We demonstrate that the sizes of the modules can be dynamically driven by varying the complexities of the tasks. The network serves as a simple example of an artificial neural network with an adaptable modular structure. This study was motivated by related dynamical nature of modules in animal brains.
URI: http://hdl.handle.net/10397/5394
ISSN: 1539-3755 (print)
1550-2376 (online)
DOI: 10.1103/PhysRevE.58.3673
Rights: Physical Review E © 1998 The American Physical Society. The Journal's web site is located at http://pre.aps.org/
Appears in Collections:Journal/Magazine Article

Files in This Item:
File Description SizeFormat 
Lam_Formation_Modules_Neural.pdf127.78 kBAdobe PDFView/Open
Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

2
Last Week
0
Last month
0
Citations as of Mar 18, 2017

WEB OF SCIENCETM
Citations

3
Last Week
0
Last month
0
Citations as of Mar 17, 2017

Page view(s)

129
Last Week
2
Last month
Checked on Mar 19, 2017

Download(s)

69
Checked on Mar 19, 2017

Google ScholarTM

Check

Altmetric



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