A Task Decomposition Algorithm Using Mixtures of Normal Distributions for Classification Problems

Auckland, New Zealand December 13-December 15

DOI Bookmark:

http://doi.ieeecomputersociety.org/10.1109/HIS.2006.9

Sixth International Conference on Hyb ...

	This Article
	PURCHASE ARTICLE: $19 PDF HTML IEEE Xplore Subscribers
	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 Seiji Ishihara Articles by Harukazu Igarashi

	ASCII Text	x
	Seiji Ishihara, Harukazu Igarashi, "A Task Decomposition Algorithm Using Mixtures of Normal Distributions for Classification Problems," Hybrid Intelligent Systems, International Conference on, pp. 28, Sixth International Conference on Hybrid Intelligent Systems (HIS'06), 2006.

	BibTex	x
	@article{ 10.1109/HIS.2006.9, author = {Seiji Ishihara and Harukazu Igarashi}, title = {A Task Decomposition Algorithm Using Mixtures of Normal Distributions for Classification Problems}, journal ={Hybrid Intelligent Systems, International Conference on}, volume = {0}, year = {2006}, isbn = {0-7695-2662-4}, pages = {28}, doi = {http://doi.ieeecomputersociety.org/10.1109/HIS.2006.9}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }

	RefWorks Procite/RefMan/Endnote	x
	TY - CONF JO - Hybrid Intelligent Systems, International Conference on TI - A Task Decomposition Algorithm Using Mixtures of Normal Distributions for Classification Problems SN - 0-7695-2662-4 SP EP A1 - Seiji Ishihara, A1 - Harukazu Igarashi, PY - 2006 KW - null VL - 0 JA - Hybrid Intelligent Systems, International Conference on ER -

Seiji Ishihara, Kinki University, Japan

Harukazu Igarashi, Shibaura Institute of Technology, Japan

This paper proposes an algorithm for decomposing a multi-class classification problem into a set of two-class classification problems. The algorithm divides a set of input pattern vectors in each class into subsets according to the distribution of the selected input pattern vectors. The distribution is represented by a mixture of normal distributions, and the number of subsets is defined by using MDL criterion. The algorithm can be applied for constructing an effective modular neural network. We show also the experimental results of the construction and the advantages of the algorithm.

Citation:

Seiji Ishihara, Harukazu Igarashi, "A Task Decomposition Algorithm Using Mixtures of Normal Distributions for Classification Problems," his, pp.28, Sixth International Conference on Hybrid Intelligent Systems (HIS'06), 2006

Peer Review Notice | Give Us Feedback

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