Evolutionary Strategy for Learning Multiple-Valued Logic Functions

	This Article
	Subscribers, please Login Purchase article: $19 PDF IEEE Xplore Subscribers RSS feed
	Share
	Email this Article to a friend
	Bibliographic References
	ASCII Text BibTex RefWorks Procite/RefMan/Endnote
	Add to:
	Digg Furl Spurl Blink Simpy Google Del.icio.us Y!MyWeb
	Search
	Similar Articles Articles by Alioune Ngom Articles by Dan A. Simovici Articles by Ivan Stojmenović

34th International Symposium on Multiple-Valued Logic (ISMVL'04)

University of Toronto, Toronto, Canada

May 19-May 22

ISBN: 0-7695-2130-4

	ASCII Text	x
	Alioune Ngom, Dan A. Simovici, Ivan Stojmenović, "Evolutionary Strategy for Learning Multiple-Valued Logic Functions," Multiple-Valued Logic, IEEE International Symposium on, pp. 154-160, 34th International Symposium on Multiple-Valued Logic (ISMVL'04), 2004.

	BibTex	x
	@article{ 10.1109/ISMVL.2004.1319935, author = {Alioune Ngom and Dan A. Simovici and Ivan Stojmenović}, title = {Evolutionary Strategy for Learning Multiple-Valued Logic Functions}, journal ={Multiple-Valued Logic, IEEE International Symposium on}, volume = {0}, year = {2004}, issn = {0195-623X}, pages = {154-160}, doi = {http://doi.ieeecomputersociety.org/10.1109/ISMVL.2004.1319935}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }

	RefWorks Procite/RefMan/Endnote	x
	TY - CONF JO - Multiple-Valued Logic, IEEE International Symposium on TI - Evolutionary Strategy for Learning Multiple-Valued Logic Functions SN - 0195-623X SP154 EP160 A1 - Alioune Ngom, A1 - Dan A. Simovici, A1 - Ivan Stojmenović, PY - 2004 KW - Multiple-valued logic KW - Multiple-threshold perceptron KW - Evolution strategy KW - Neural network KW - Partitioning method KW - Constructive algorithm VL - 0 JA - Multiple-Valued Logic, IEEE International Symposium on ER -

Alioune Ngom, University of Windsor

Dan A. Simovici, University of Massachusetts at Boston

Ivan Stojmenović, University of Ottawa

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ISMVL.2004.1319935

We consider the problem of synthesizing multiple-valued logic functions by neural networks. An evolutionary strategy (ES) which finds the longest strip in V \subseteq K^n described. A strip contains points located between two parallel hyperplanes. Repeated application of ES partitions the space V into certain number of strips, each of them corresponding to a hidden unit. We construct neural networks based on these hidden units. Preliminary experimental results are presented and discussed.

Index Terms:

Multiple-valued logic, Multiple-threshold perceptron, Evolution strategy, Neural network, Partitioning method, Constructive algorithm

Citation:

Alioune Ngom, Dan A. Simovici, Ivan Stojmenović, "Evolutionary Strategy for Learning Multiple-Valued Logic Functions," ismvl, pp.154-160, 34th International Symposium on Multiple-Valued Logic (ISMVL'04), 2004

Peer Review Notice | Give Us Feedback

Usage of this product signifies your acceptance of the Terms of Use.