ON LEARNING kDNF^s_n BOOLEAN FORMULAS

	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 Arturo Hernandez-Aguirre Articles by Bill P. Buckles Articles by Carlos A. Coello Coello

The Third NASA/DoD Workshop on Evolvable Hardware

Long Beach, Cailfornia

July 12-July 14

ISBN: 0-7695-1180-5

	ASCII Text	x
	Arturo Hernandez-Aguirre, Bill P. Buckles, Carlos A. Coello Coello, "ON LEARNING kDNF^s_n BOOLEAN FORMULAS," Evolvable Hardware, NASA/DoD Conference on, pp. 0240, The Third NASA/DoD Workshop on Evolvable Hardware, 2001.

	BibTex	x
	@article{ 10.1109/EH.2001.937967, author = {Arturo Hernandez-Aguirre and Bill P. Buckles and Carlos A. Coello Coello}, title = {ON LEARNING kDNF^s_n BOOLEAN FORMULAS}, journal ={Evolvable Hardware, NASA/DoD Conference on}, volume = {0}, year = {2001}, isbn = {0-7695-1180-5}, pages = {0240}, doi = {http://doi.ieeecomputersociety.org/10.1109/EH.2001.937967}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }

	RefWorks Procite/RefMan/Endnote	x
	TY - CONF JO - Evolvable Hardware, NASA/DoD Conference on TI - ON LEARNING kDNF^s_n BOOLEAN FORMULAS SN - 0-7695-1180-5 SP EP A1 - Arturo Hernandez-Aguirre, A1 - Bill P. Buckles, A1 - Carlos A. Coello Coello, PY - 2001 VL - 0 JA - Evolvable Hardware, NASA/DoD Conference on ER -

Arturo Hernandez-Aguirre, Tulane University

Bill P. Buckles, Tulane University

Carlos A. Coello Coello, CINVESTAV-IPN

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/EH.2001.937967

Abstract: The number of samples needed to learn an instance of the representation class kDNF^s_n of Boolean formulas is predicted using some tolerance parameters by the PAC framework. When the learning machine is a simple genetic algorithm, the initial population is an issue. Using PAC-learning we derive the population size that has at least one individual at a given Hamming distance from the optimum. Then we show that the GA evolves solutions from initial populations rather far (Hamming distance) from the optimum.

Citation:

Arturo Hernandez-Aguirre, Bill P. Buckles, Carlos A. Coello Coello, "ON LEARNING kDNF^s_n BOOLEAN FORMULAS," eh, pp.0240, The Third NASA/DoD Workshop on Evolvable Hardware, 2001

Peer Review Notice | Give Us Feedback

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