File(s) under permanent embargo
Knowledge extraction from a mixed transfer function artificial neural network
conference contribution
posted on 2004-01-01, 00:00 authored by I Khan, Yakov Frayman, Saeid NahavandiOne 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.
History
Title of proceedings
InTech'04 : Proceedings of the 5th International Conference on Intelligent TechnologiesEvent
International Conference on Intelligent Technologies (5th : 2004 : Houston, Texas)Pagination
1 - 6Publisher
University of Houston-DowntownLocation
Houston, TexasPlace of publication
Houston, TxStart date
2004-12-02End date
2004-12-04Language
engPublication classification
E1 Full written paper - refereedEditor/Contributor(s)
R AloUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC