A Partitioned Fuzzy ARTMAP Implementation for Fast Processing of Large Databases on Sequential Machines
نویسندگان
چکیده
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 FAM architectures. Directions for future work are also discussed.
منابع مشابه
Pipelining of Fuzzy ARTMAP without matchtracking: Correctness, performance bound, and Beowulf evaluation
Fuzzy ARTMAP neural networks have been proven to be good classifiers on a variety of classification problems. However, the time that Fuzzy ARTMAP takes to converge to a solution increases rapidly as the number of patterns used for training is increased. In this paper we examine the time Fuzzy ARTMAP takes to converge to a solution and we propose a coarse grain parallelization technique, based o...
متن کاملCross-validation in Fuzzy ARTMAP for large databases
In this paper we are examining the issue of overtraining in Fuzzy ARTMAP. Over-training in Fuzzy ARTMAP manifests itself in two different ways: (a) it degrades the generalization performance of Fuzzy ARTMAP as training progresses; and (b) it creates unnecessarily large Fuzzy ARTMAP neural network architectures. In this work, we are demonstrating that overtraining happens in Fuzzy ARTMAP and we ...
متن کاملData-partitioning using the Hilbert space filling curves: Effect on the speed of convergence of Fuzzy ARTMAP for large database problems
The Fuzzy ARTMAP algorithm has been proven to be one of the premier neural network architectures for classification problems. One of the properties of Fuzzy ARTMAP, which can be both an asset and a liability, is its capacity to produce new nodes (templates) on demand to represent classification categories. This property allows Fuzzy ARTMAP to automatically adapt to the database without having t...
متن کاملInteger-Encoded Massively Parallel Processing of Fast-Learning Fuzzy ARTMAP Neural Networks
In this paper we develop techniques that are suitable for the parallel implementation of Fuzzy ARTMAP networks. Speedup and learning performance results are provided for execution on a DECmpp/Sx-1208 parallel processor consisting of a DEC RISC Workstation Front-End (FE) and MasPar MP-1 Back-End (BE) with 8,192 processors. Experiments of the parallel implementation were conducted on the Letters ...
متن کاملCross-Validation in Fuzzy ARTMAP Neural Networks for Large Sample Classification Problems
In this paper we are examining the issue of overtraining in Fuzzy ARTMAP. Over-training in Fuzzy ARTMAP manifests itself in two different ways: (a) it degrades the generalization performance of Fuzzy ARTMAP as training progresses, and (b) it creates unnecessarily large Fuzzy ARTMAP neural network architectures. In this work we are demonstrating that overtraining happens in Fuzzy ARTMAP and we p...
متن کامل