Abstract
A novel ART-based neural classifier closely related to Fuzzy ARTMAP (FAM) and the classifying Fuzzy Min-Max Network (FMMN) of Simpson is presented. It emerged from the need to overcome the category proliferation problem. This problem consists in creating an excessive number of prototypes needed to represent pattern clusters in the input space and their relations to the output space. Due to overtraining, FAM and FMMN often form redundant prototypes which leads to increase in resource requirements. In contrast to some recent solutions of the category proliferation problem, the proposed ART-based Fuzzy Classifier (AFC) can alleviate it while preserving a very important ART property, namely the on-line learning ability. AFC differs from FAM and FMMN in several key aspects. First, it uses a non-flat asymmetric choice function calculated on the basis of the positions of cluster centroids. It also utilizes different concepts of hyperbox size control and overlap resolving.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Carpenter, G.A., Grossberg, S., Markuzon, N., Reynolds, J.H., Rosen, D.B.: Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps. IEEE Transactions on Neural Networks 3, 698–713 (1992)
Simpson, P.K.: Fuzzy min-max neural networks – part 1: Classification. IEEE transactions on Neural Networks 3, 776–786 (1992)
Sanchez, E.G., Dimitriadis, Y.A., Cano, J.M., Coronado, J.L.: MicroARTMAP: use of mutual information for category reduction in Fuzzy ARTMAP. In: Proceedings of IJCNN 2000, vol. 6, pp. 647–652 (2000)
Sanchez, E.G., Dimitriadis, Y.A., Cano, J.M., Coronado, J.L.: Safe- μARTMAP: A new solution for reducing category proliferation in Fuzzy ARTMAP. In: Proceedings of IJCNN 2001, pp. 1221–1226 (2001)
Verzi, S.J., Heileman, G.L., Georgiopoulos, M., Healy, M.J.: Boosting in ARTMAP networks. In: Proceedings of SCI 2000, vol. 3, pp. 473-478 (2000)
Georgiopoulos, M., Koufakou, A., Anagnostopoulos, G.C., Kasparis, T.: Overtraining in Fuzzy ARTMAP: myth or reality? In: Proceedings of IJCNN 2001, vol. 2, pp. 1186–1190 (2001)
Marriott, S., Harrison, R.F.: A modified Fuzzy ARTMAP architecture for the approximation of noisy mappings. Neural Networks 8, 619–641 (1995)
Williamson, J.R.: Gaussian ARTMAP: a neural network for fast incremental learning of noisy multidimensional maps. Neural Networks 9, 881–897 (1996)
Carpenter, G.A., Milenova, B.L., Noeske, B.W.: Distributed ARTMAP: a neural network for fast distributed supervised learning. Neural Networks 11, 793–813 (1998)
Lim, C.P., Harrison, R.F.: Modified Fuzzy ARTMAP approaches Bayes optimal classification rates: an empirical demonstration. Neural Networks 10, 755–774 (1997)
Anagnostopoulos, G.C., Georgiopoulos, M.: Ellipsoid ART and ARTMAP for incremental clustering and classification. In: Proceedings of IJCNN 2001, vol. 2, pp. 1221–1226 (2001)
Hernández, E.P., Sanchez, E.G., Dimitriadis, Y.A., Coronado, J.L.: A neurofuzzy system that uses distributed learning for compact rule set generation. In: Proceedings of the IEEE International Conference on System, Man and Cybernetics, vol. 3, pp. 441–446 (1999)
Lee, H.-M., Lai, C.-S.: Supervised Fuzzy ART: training of a neural network for pattern classification via combining supervised and unsupervised learning. In: Proceedings of ICNN 1993, pp. 323–328 (1993)
Cano, J.M., Dimitriadis, Y.A., Sanchez, E.G., Coronado, J.L.: Learning from noisy information in FasArt and FasBack neuro-fuzzy systems. Neural Networks 14, 407–425 (2001)
Blake, C.L., Merz, C.J.: UCI Repository of machine learning databases. University of California, Department of Information and Computer Science, Irvine, CA, http://www.ics.uci.edu/~mlearn/MLRepository.html
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sapozhnikova, E.P., Rosenstiel, W. (2003). AFC: ART-Based Fuzzy Classifier. In: Palade, V., Howlett, R.J., Jain, L. (eds) Knowledge-Based Intelligent Information and Engineering Systems. KES 2003. Lecture Notes in Computer Science(), vol 2774. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45226-3_5
Download citation
DOI: https://doi.org/10.1007/978-3-540-45226-3_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40804-8
Online ISBN: 978-3-540-45226-3
eBook Packages: Springer Book Archive