J. Castro, J. Secretan, M. Georgiopoulos, R. F. DeMara, G. Anagnostopoulos, and A. J. Gonzalez, "Pipelining of Fuzzy-ARTMAP without Match-Tracking: Correctness, Performance Bound, and Beowulf Evaluation," submitted to Neural Networks on December 27, 2004. Abstract: Fuzzy ARTMAP neural networks have been proven to be good classifiers on a variety of classification problems. However, the time that it takes Fuzzy ARTMAP to converge to a solution increases rapidly as the number of patterns used for training increases. In this paper we examine the time that it takes Fuzzy ARTMAP to converge to a solution and we propose a coarse grain parallelization technique, based on a pipeline approach, to speed-up the training process. In particular, we have parallelized Fuzzy ARTMAP, without the match-tracking mechanism. We provide a series of theorems and associated proofs that show the characteristics of Fuzzy ARTMAP's, without matchtracking, parallel implementation. Results run on a BEOWULF cluster with three large databases show linear speedup in the number of processors used in the pipeline. The databases used for our experiments are the Forrest Covertype database from the UCI Machine Learning repository and two arti cial databases, where the data generated were 16-dimensional Gaussianly distributed data belonging to two distinct classes, with different amounts of overlap (5 % and 15 %).