Author :
Verzi, Stephen J. ; Heileman, Gregory L. ; Georgiopoulos, Michael ; Healy, Michael J.
Author_Institution :
Dept. of Comput. Sci., New Mexico Univ., Albuquerque, NM, USA
Abstract :
We present a modification to the fuzzy ARTMAP neural network architecture for conducting boosted learning in a probabilistic setting. We call this new architecture boosted ARTMAP (BARTMAP). Performance comparison with fuzzy ARTMAP, PROBART and ART-EMAP on some simple two-class problems is discussed. Experimental results indicate that BARTMAP gives better generalization results on some problems involving classification overlap. In addition BARTMAP requires fewer resources, i.e., network nodes, to achieve performance levels comparable to those in fuzzy ARTMAP
Keywords :
ART neural nets; fuzzy neural nets; neural net architecture; pattern classification; ART-EMAP; PROBART; boosted ARTMAP; boosted learning; classification overlap; fuzzy ARTMAP neural network architecture; generalization; probabilistic learning; two-class problems; Boosting; Computational complexity; Computer architecture; Computer science; Fuzzy neural networks; Fuzzy sets; Machine learning algorithms; Neural networks; Subspace constraints; Training data;
Conference_Titel :
Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on
Conference_Location :
Anchorage, AK
Print_ISBN :
0-7803-4859-1
DOI :
10.1109/IJCNN.1998.682299
