José Castro, Michael Georgiopoulos, Ronald Demara, and Avelino Gonzalez
Fuzzy ARTMAP (FAM) is a neural network architecture that can establish the correct mapping between reavalued 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 slowdown 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 FAM architectures. Directions for future work are also discussed.