J. Castro, M. Georgiopoulos, R. F. DeMara, and A. J. Gonzalez, "A Partitioned 
Fuzzy ARTMAP Implementation for Fast Processing of Large Databases on Sequential 
Machines," in Proceedings of the Seventieth International Florida Artificial 
Intelligence Research Symposium (FLAIRS'04), Miami Beach, Florida, U.S.A., May 
17 - 19, 2004.

Abstract
Fuzzy ARTMAP (FAM) is a neural network architecture that can establish the 
correct mapping between real valued input patterns and their correct labels. FAM 
can learn quickly compared to other neural network paradigms and has the 
advantage of incremental/online learning capabilities. Nevertheless FAM tends to 
slow down as the size of the data set grows. This problem is analyzed and a 
solution is proposed that can speed up the algorithm in sequential as well as 
parallel settings. Experimental results are presented that show a considerable 
improvement in speed of the algorithm at the cost of creating larger size 
FAMarchitectures. Directions for future work are also discussed.