### 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 RBF network, whose parameters are estimated according to the evaluation based on MDL criterion. In this paper, the algorithm applied for constructing a modular neural network. Experimental results showed that the algorithm simplifies multi-class classification problems effectively.

Original language | English |
---|---|

Title of host publication | Proceedings of the Digital Imaging Computing |

Subtitle of host publication | Techniques and Applications, DICTA 2005 |

Pages | 2-7 |

Number of pages | 6 |

DOIs | |

Publication status | Published - 2005 Dec 1 |

Event | Digital Imaging Computing: Techniques and Applications, DICTA 2005 - Cairns, Australia Duration: 2005 Dec 6 → 2005 Dec 8 |

### Publication series

Name | Proceedings of the Digital Imaging Computing: Techniques and Applications, DICTA 2005 |
---|---|

Volume | 2005 |

### Conference

Conference | Digital Imaging Computing: Techniques and Applications, DICTA 2005 |
---|---|

Country | Australia |

City | Cairns |

Period | 05/12/6 → 05/12/8 |

### ASJC Scopus subject areas

- Engineering(all)

## Fingerprint Dive into the research topics of 'A task decomposition algorithm using radial basis functions for classification problems'. Together they form a unique fingerprint.

## Cite this

Ishihara, S., & Igarashi, H. (2005). A task decomposition algorithm using radial basis functions for classification problems. In

*Proceedings of the Digital Imaging Computing: Techniques and Applications, DICTA 2005*(pp. 2-7). [1578100] (Proceedings of the Digital Imaging Computing: Techniques and Applications, DICTA 2005; Vol. 2005). https://doi.org/10.1109/DICTA.2005.1578100