Title :
A Task Decomposition Algorithm Using Radial Basis Functions for Classification Problems
Author :
Ishihara, Seiji ; Igarashi, Harukazu
Author_Institution :
Kinki University
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.
Keywords :
Classification algorithms; Computer applications; Digital images; Large-scale systems; Neural networks; Parameter estimation; Pattern classification; Radial basis function networks; Sampling methods; Supervised learning;
Conference_Titel :
Digital Image Computing: Techniques and Applications, 2005. DICTA '05. Proceedings 2005
Conference_Location :
Queensland, Australia
Print_ISBN :
0-7695-2467-2
DOI :
10.1109/DICTA.2005.8