Q'tron Neural Networks for Constraint Satisfaction

H
HIS
2004
Fourth International Conference on Hybrid Intelligent Systems (HIS'04)
Abstract - Q'tron Neural Networks for Constraint Satisfaction

	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
	Add to:
	Digg Furl Spurl Blink Simpy Google Del.icio.us Y!MyWeb
	Search
	Similar Articles Articles by Tai-Wen Yue Articles by Mei-Ching Chen

Fourth International Conference on Hybrid Intelligent Systems (HIS'04)

Kitakyushu, Japan

December 05-December 08

ISBN: 0-7695-2291-2

	ASCII Text	x
	Tai-Wen Yue, Mei-Ching Chen, "Q'tron Neural Networks for Constraint Satisfaction," Hybrid Intelligent Systems, International Conference on, pp. 398-403, Fourth International Conference on Hybrid Intelligent Systems (HIS'04), 2004.

	BibTex	x
	@article{ 10.1109/ICHIS.2004.77, author = {Tai-Wen Yue and Mei-Ching Chen}, title = {Q'tron Neural Networks for Constraint Satisfaction}, journal ={Hybrid Intelligent Systems, International Conference on}, volume = {0}, year = {2004}, isbn = {0-7695-2291-2}, pages = {398-403}, doi = {http://doi.ieeecomputersociety.org/10.1109/ICHIS.2004.77}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }

	RefWorks Procite/RefMan/Endnote	x
	TY - CONF JO - Hybrid Intelligent Systems, International Conference on TI - Q'tron Neural Networks for Constraint Satisfaction SN - 0-7695-2291-2 SP398 EP403 A1 - Tai-Wen Yue, A1 - Mei-Ching Chen, PY - 2004 KW - null VL - 0 JA - Hybrid Intelligent Systems, International Conference on ER -

Tai-Wen Yue, Tatung University, Taipei, Taiwan

Mei-Ching Chen, Tatung University, Taipei, Taiwan

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICHIS.2004.77

This paper proposes the methods to solve the constraint satisfaction problems (CSPs) using Q'tron neural networks (NNs). A Q'tron NN is local-minima free if it is built as a known-energy system and is incorporated with the proposed persistent noise-injection mechanism. The so-built Q'tron NN, as a result, will settle down if and only if a feasible solution is found. Additionally, such a Q'tron NN is intrinsically auto-reversible. This renders the NN operable in a question-answering mode for extracting interested information. A concrete example, i.e., to solve the N-queen problem, will be demonstrated to highlight the main concept.

Citation:

Tai-Wen Yue, Mei-Ching Chen, "Q'tron Neural Networks for Constraint Satisfaction," his, pp.398-403, Fourth International Conference on Hybrid Intelligent Systems (HIS'04), 2004

Peer Review Notice | Give Us Feedback

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