A task decomposition algorithm using mixtures of normal distributions for classification problems

Seiji Ishihara, Harukazu Igarashi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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.

Original languageEnglish
Title of host publicationProceedings - Sixth International Conference on Hybrid Intelligent Systems and Fourth Conference on Neuro-Computing and Evolving Intelligence, HIS-NCEI 2006
DOIs
Publication statusPublished - 2006
Event6th International Conference on Hybrid Intelligent Systems and 4th Conference on Neuro-Computing and Evolving Intelligence, HIS-NCEI 2006 - Auckland
Duration: 2006 Dec 132006 Dec 15

Other

Other6th International Conference on Hybrid Intelligent Systems and 4th Conference on Neuro-Computing and Evolving Intelligence, HIS-NCEI 2006
CityAuckland
Period06/12/1306/12/15

Fingerprint

Normal distribution
Decomposition
Neural networks

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Ishihara, S., & Igarashi, H. (2006). A task decomposition algorithm using mixtures of normal distributions for classification problems. In Proceedings - Sixth International Conference on Hybrid Intelligent Systems and Fourth Conference on Neuro-Computing and Evolving Intelligence, HIS-NCEI 2006 [4041408] https://doi.org/10.1109/HIS.2006.264911

A task decomposition algorithm using mixtures of normal distributions for classification problems. / Ishihara, Seiji; Igarashi, Harukazu.

Proceedings - Sixth International Conference on Hybrid Intelligent Systems and Fourth Conference on Neuro-Computing and Evolving Intelligence, HIS-NCEI 2006. 2006. 4041408.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ishihara, S & Igarashi, H 2006, A task decomposition algorithm using mixtures of normal distributions for classification problems. in Proceedings - Sixth International Conference on Hybrid Intelligent Systems and Fourth Conference on Neuro-Computing and Evolving Intelligence, HIS-NCEI 2006., 4041408, 6th International Conference on Hybrid Intelligent Systems and 4th Conference on Neuro-Computing and Evolving Intelligence, HIS-NCEI 2006, Auckland, 06/12/13. https://doi.org/10.1109/HIS.2006.264911
Ishihara S, Igarashi H. A task decomposition algorithm using mixtures of normal distributions for classification problems. In Proceedings - Sixth International Conference on Hybrid Intelligent Systems and Fourth Conference on Neuro-Computing and Evolving Intelligence, HIS-NCEI 2006. 2006. 4041408 https://doi.org/10.1109/HIS.2006.264911
Ishihara, Seiji ; Igarashi, Harukazu. / A task decomposition algorithm using mixtures of normal distributions for classification problems. Proceedings - Sixth International Conference on Hybrid Intelligent Systems and Fourth Conference on Neuro-Computing and Evolving Intelligence, HIS-NCEI 2006. 2006.
@inproceedings{fdc0d6dd23064d1c933ead46169d61ce,
title = "A task decomposition algorithm using mixtures of normal distributions for classification problems",
abstract = "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.",
author = "Seiji Ishihara and Harukazu Igarashi",
year = "2006",
doi = "10.1109/HIS.2006.264911",
language = "English",
isbn = "0769526624",
booktitle = "Proceedings - Sixth International Conference on Hybrid Intelligent Systems and Fourth Conference on Neuro-Computing and Evolving Intelligence, HIS-NCEI 2006",

}

TY - GEN

T1 - A task decomposition algorithm using mixtures of normal distributions for classification problems

AU - Ishihara, Seiji

AU - Igarashi, Harukazu

PY - 2006

Y1 - 2006

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=40249090253&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=40249090253&partnerID=8YFLogxK

U2 - 10.1109/HIS.2006.264911

DO - 10.1109/HIS.2006.264911

M3 - Conference contribution

SN - 0769526624

SN - 9780769526621

BT - Proceedings - Sixth International Conference on Hybrid Intelligent Systems and Fourth Conference on Neuro-Computing and Evolving Intelligence, HIS-NCEI 2006

ER -