Fuzzy Clustering Neural Network (FCNN): Competitive Learning and Parallel Architecture

Article type: Research Article

Authors: Zhang, D. | Kamel, M. | Elmasry, M.I.

Affiliations: VLSI Research Group, Department of Electrical and Computer Engineering | Pattern Analysis and Machine Intelligence Group, Department of Systems Design Engineering, University of Waterloo, Waterloo, Ontario N2L 3G1, Canada

Abstract: This article presents a fuzzy clustering neural network (FCNN) model that uses Gaussian nonlinearity. A learning algorithm, based on direct fuzzy competition between the nodes, is introduced. The connecting weights, which are adaptively updated in batch mode, converge towards values that are representative of the clustering structure of the input patterns. Mapping the proposed algorithm onto the corresponding architecture with three types of processing cells, it is feasible to implement the FCNN in parallel. The effectiveness of the FCNN is illustrated by applying the model to a number of test data sets, analyzing the hardware complexity of the architecture, and comparing the performance to that of fuzzy c-means (FCM) algorithm.

DOI: 10.3233/IFS-1994-2402

Journal: Journal of Intelligent and Fuzzy Systems, vol. 2, no. 4, pp. 289-298, 1994