Gaussian Artmap: A Neural Network for Fast Incremental Learning of Noisy Multidimensional Maps
OA Version
Citation
Abstract
A new neural network architecture for incremental supervised learning of analalog multidimensional maps is introduced. The architecture, called Gaussian ARTMAP, is a synthesis of a Gaussian classifier and an Adaptive Resonance Theory (ART) neural network, achieved by defining the ART choice function as the discriminant function of a Gaussian classifer with separable distributions, and the ART match function as the same, but with the a priori probabilities of the distributions discounted. While Gaussian ARTMAP retains the attractive parallel computing and fast learning properties of fuzzy ARTMAP, it learns a more efficient internal representation of a mapping while being more resistant to noise than fuzzy ARTMAP on a number of benchmark databases. Several simulations are presented which demonstrate that Gaussian ARTMAP consistently obtains a better trade-off of classification rate to number of categories than fuzzy ARTMAP. Results on a vowel classiflcation problem are also presented which demonstrate that Gaussian ARTMAP outperforms many other classifiers.
Description
License
Copyright 1995 Boston University. Permission to copy without fee all or part of this material is granted provided that: 1. The copies are not made or distributed for direct commercial advantage; 2. the report title, author, document number, and release date appear, and notice is given that copying is by permission of BOSTON UNIVERSITY TRUSTEES. To copy otherwise, or to republish, requires a fee and / or special permission.