Abstract:
A neural network architecture is introduced for incremental supervised learning of recognition categories and multidimensional maps in response to arbitrary sequences of ...Show MoreMetadata
Abstract:
A neural network architecture is introduced for incremental supervised learning of recognition categories and multidimensional maps in response to arbitrary sequences of analog or binary input vectors, which may represent fuzzy or crisp sets of features. The architecture, called fuzzy ARTMAP, achieves a synthesis of fuzzy logic and adaptive resonance theory (ART) neural networks by exploiting a close formal similarity between the computations of fuzzy subsethood and ART category choice, resonance, and learning. Four classes of simulation illustrated fuzzy ARTMAP performance in relation to benchmark backpropagation and generic algorithm systems. These simulations include finding points inside versus outside a circle, learning to tell two spirals apart, incremental approximation of a piecewise-continuous function, and a letter recognition database. The fuzzy ARTMAP system is also compared with Salzberg's NGE systems and with Simpson's FMMC system.<>
Published in: IEEE Transactions on Neural Networks ( Volume: 3, Issue: 5, September 1992)
DOI: 10.1109/72.159059
References is not available for this document.
Select All
1.
G. A. Carpenter, S. Grossberg and J. H. Reynolds, "ARTMAP: Supervised real-time learning and classification of nonstationary data by a self-organizing neural network", Neural Networks, vol. 4, pp. 565-588, 1991.
2.
Tech. Rep. CAS/CNS-TR-91-001. Boston, MA: Boston University. Reprinted in [3].
3.
G. A. Carpenter and S. Grossberg, "A massively parallel architecture for a self-organizing neural pattern recognition machine", Computer Vision Graphics and Image Processing, vol. 37, pp. 54-115, 1987.
4.
G. A. Carpenter and S. Grossberg, Pattern Recognition by Self-Organizing Neural Networks, MA, Cambridge:MIT Press, 1991.
5.
G. A. Carpenter, S. Grossberg and D. B. Rosen, "Fuzzy ART: An adaptive resonance algorithm for rapid stable classification of analog patterns", Proc. Int. Joint Conf. Neural Networks, vol. II, pp. 411-420.
6.
G.A. Carpenter, S. Grossberg and D.B. Rosen, "Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system", Neural Networks, vol. 4, pp. 759-771, 1991.
7.
8.
B. Kosko, "Fuzzy entropy and conditioning", Inform. Sci., vol. 40, pp. 165-174, 1986.
10.
J. C. Bezdek, Pattern Recognition with Fuzzy Objective Function Algorithms, New York:Plenum Press, 1981.
11.
S. Pal and D. K. D. Majumder, Fuzzy Mathematical Approach to Pattern Recognition, New York:Wiley, 1986.
12.
G. A. Carpenter, S. Grossberg and D. B. Rosen, A neural network realization of fuzzy ART, 1991.
13.
S. L. Salzberg, Learning with nested generalized exemplars, 1989.
14.
S. L. Salzberg, Learning with Nested Generalized Exemplars, MA, Hingham:Kluwer Academic, 1990.
15.
S. L. Salzberg, "A nearest hyperrectangle learning method", Machine Learning, vol. 6, pp. 251-276, 1991.
16.
P. Simpson, "Fuzzy min-max classification with neural networks", Heuristics: J. Knowledge Eng., vol. 4, pp. 1-9, 1991.
17.
G. Wilensky, "Analysis of neural network issues: Scaling enhanced nodal processing comparison with standard classification", DARPA Neural Network Program Review, Oct. 1990.
18.
K. J. Lang and M. J. Witbrock, "Learning to tell two spirals apart", Proc. 1988 Connectionist Models Summer School, pp. 52-59, 1989.
19.
P. W. Frey and D. J. Slate, "Letter recognition using Holland-style adaptive classifiers", Machine Learning, vol. 6, pp. 161-182, 1991.
20.
J. H. Holland, Adaptation in Natural and Artificial Systems, MI, Ann Arbor:University of Michigan Press, 1975.
21.
J. H. Holland, "Adaptive algorithms for discovering and using general patterns in growing knowledge bases", Int. J. Policy Analysis and Information Systems, vol. 4, pp. 217-240, 1980.
22.
J. H. Holland, "Escaping brittleness: The possibilities of general purpose machine learning algorithms applied to parallel rule-based systems" in Machine Learning: An Artificial Intelligence Approach, CA, San Mateo:Morgan Kaufmann, vol. II, 1986.
23.
Β. Moore, "ART 1 and pattern clustering", Proc. 1988 Connectionist Models Summer School, pp. 174-185, 1989.
24.
D. E. Rumelhart, G. Hinton and R. Williams, "Learning internal representations by error propagation" in Parallel Distributed Processing, MA, Cambridge:MIT Press, 1986.
25.
S. E. Fahlman, "Faster-learning variations on back-propagation: An empirical study", Proc. 1988 Connectionist Models Summer School, pp. 38-51, 1989.
