Knowledge extraction from a mixed transfer function artificial neural network

Khan, I., Frayman, Yakov and Nahavandi, Saeid 2004, Knowledge extraction from a mixed transfer function artificial neural network, in InTech'04 : Proceedings of the 5th International Conference on Intelligent Technologies, University of Houston-Downtown, Houston, Tx, pp. 1-6.

Attached Files
Name Description MIMEType Size Downloads

Title Knowledge extraction from a mixed transfer function artificial neural network
Author(s) Khan, I.
Frayman, Yakov
Nahavandi, SaeidORCID iD for Nahavandi, Saeid orcid.org/0000-0002-0360-5270
Conference name International Conference on Intelligent Technologies (5th : 2004 : Houston, Texas)
Conference location Houston, Texas
Conference dates 2-4 December 2004
Title of proceedings InTech'04 : Proceedings of the 5th International Conference on Intelligent Technologies
Editor(s) Alo, Richard
Publication date 2004
Start page 1
End page 6
Publisher University of Houston-Downtown
Place of publication Houston, Tx
Summary One of the big problems with Artificial Neural Networks (ANN) is that their results are not intuitively clear. For example, if we use the traditional neurons, with a sigmoid activation function, we can approximate any function, including linear functions, but the coefficients (weights) in this approximation will be rather meaningless. To resolve this problem, this paper presents a novel kind of ANN with different transfer functions mixed together. The aim of such a network is to i) obtain a better generalization than current networks ii) to obtain knowledge from the networks without a sophisticated knowledge extraction algorithm iii) to increase the understanding and acceptance of ANNs. Transfer Complexity Ratio is defined to make a sense of the weights associated with the network. The paper begins with a review of the knowledge extraction from ANNs and then presents a Mixed Transfer Function Artificial Neural Network (MTFANN). A MTFANN contains different transfer functions mixed together rather than mono-transfer functions. This mixed presence has helped to obtain high level knowledge and similar generalization comparatively to monotransfer function nets in a global optimization context.
Language eng
Field of Research 090699 Electrical and Electronic Engineering not elsewhere classified
HERDC Research category E1 Full written paper - refereed
Persistent URL http://hdl.handle.net/10536/DRO/DU:30005552

Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 0 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 953 Abstract Views, 1 File Downloads  -  Detailed Statistics
Created: Mon, 07 Jul 2008, 09:51:08 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.