Task decomposition and module combination based on class relations: a modular neural network for pattern classification
Authors:
- M. ItoMIM. Ito
- 1 September 1999
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 10 (5) , 1244-1256
Abstract
We propose a method for decomposing pattern classification problems based on the class relations among training data. By using this method, we can divide a K-class classification problem into a series of (/sub 2//sup K/) two-class problems. These two-class problems are to discriminate class C/sub i/ from class C/sub j/ for i=1, ..., K and j=i+1, while the existence of the training data belonging to the other K-2 classes is ignored. If the two-class problem of discriminating class C/sub i/ from class C/sub j/ is still hard to be learned, we can further break down it into a set of two-class subproblems as small as we expect. Since each of the two-class problems can be treated as a completely separate classification problem with the proposed learning framework, all of the two-class problems can be learned in parallel. We also propose two module combination principles which give practical guidelines in integrating individual trained network modules. After learning of each of the two-class problems with a network module, we can easily integrate all of the trained modules into a min-max modular (M/sup 3/) network according to the module combination principles and obtain a solution to the original problem. Consequently, a large-scale and complex K-class classification problem can be solved effortlessly and efficiently by learning a series of smaller and simpler two-class problems in parallel.Keywords
This publication has 12 references indexed in Scilit:
- Constructive training of probabilistic neural networksNeurocomputing, 1998
- Task decomposition based on class relations: A modular neural network architecture for pattern classificationLecture Notes in Computer Science, 1997
- The min-max function differentiation and training of fuzzy neural networksIEEE Transactions on Neural Networks, 1996
- A parallel and modular multi-sieving neural network architecture for constructive learning1995
- A simplified neural network solution through problem decomposition: the case of the truck backer-upperIEEE Transactions on Neural Networks, 1993
- An improved algorithm for neural network classification of imbalanced training setsIEEE Transactions on Neural Networks, 1993
- Fuzzy min-max neural networks. I. ClassificationIEEE Transactions on Neural Networks, 1992
- Task Decomposition Through Competition in a Modular Connectionist Architecture: The What and Where Vision TasksCognitive Science, 1991
- Adaptive Mixtures of Local ExpertsNeural Computation, 1991
- Modularity and scaling in large phonemic neural networksIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989