Gaussian ARTMAP: A Neural Network for Fast Incremental Learning of Noisy Multidimensional Maps

A new neural network architecture for incremental supervised learning of analog multidimensional maps is introduced. The architecture, called Gaussian ARTMAP, is a synthesis of a Gaussian classifier and an adaptive resonance theory (ART) neural network, achieved by defining the ART choice function as the discriminant function of a Gaussian classifier with separable distributions, and the ART match function as the same, but with the distributions normalized to a unit height. While Gaussian ARTMAP retains the attractive parallel computing and fast learning properties of fuzzy ARTMAP, it learns a more efficient internal representation of a mapping while being more resistant to noise than fuzzy ARTMAP on a number of benchmark databases. SSeveral simulations are presented which demonstrate that Gaussian ARTMAP consistently obtains a better trade-off of classification rate to number of categories than fuzzy ARTMAP. Results on a vowel classification problem are also presented which demonstrate that Gaussian ARTMAP outperforms many other classifiers. Copyright 1996 Elsevier Science Ltd

[1]  J. Kruschke,et al.  ALCOVE: an exemplar-based connectionist model of category learning. , 1992, Psychological review.

[2]  Bernd Fritzke,et al.  Growing cell structures--A self-organizing network for unsupervised and supervised learning , 1994, Neural Networks.

[3]  Ah-Hwee Tan,et al.  Rule Extraction: From Neural Architecture to Symbolic Representation , 1995 .

[4]  D. Broomhead,et al.  Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks , 1988 .

[5]  Marzuki Khalid,et al.  BY FUZZY ARTMAP NEURAL NETWORK , 1997 .

[6]  Stephen Grossberg,et al.  A massively parallel architecture for a self-organizing neural pattern recognition machine , 1988, Comput. Vis. Graph. Image Process..

[7]  F. Girosi,et al.  Networks for approximation and learning , 1990, Proc. IEEE.

[8]  R. Courant,et al.  Methods of Mathematical Physics , 1962 .

[9]  Stephen Grossberg,et al.  Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps , 1992, IEEE Trans. Neural Networks.

[10]  Roman Bek,et al.  Discourse on one way in which a quantum-mechanics language on the classical logical base can be built up , 1978, Kybernetika.

[11]  Gail A. Carpenter,et al.  ART-EMAP: A neural network architecture for object recognition by evidence accumulation , 1995, IEEE Trans. Neural Networks.

[12]  Stephen Grossberg,et al.  ARTMAP: supervised real-time learning and classification of nonstationary data by a self-organizing neural network , 1991, [1991 Proceedings] IEEE Conference on Neural Networks for Ocean Engineering.

[13]  C. J. Stone,et al.  Optimal Global Rates of Convergence for Nonparametric Regression , 1982 .

[14]  Stephen Grossberg,et al.  Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system , 1991, Neural Networks.

[15]  M. J. D. Powell,et al.  Radial basis functions for multivariable interpolation: a review , 1987 .

[16]  J. Mason,et al.  Algorithms for approximation , 1987 .

[17]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[18]  Kris Popat,et al.  Novel cluster-based probability model for texture synthesis, classification, and compression , 1993, Other Conferences.

[19]  A. N. Tikhonov,et al.  Solutions of ill-posed problems , 1977 .

[20]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[21]  Stephen Grossberg,et al.  A Theory of Human Memory: Self-Organization and Performance of Sensory-Motor Codes, Maps, and Plans , 1982 .

[22]  Stephen Grossberg,et al.  Comparative performance measures of fuzzy ARTMAP, learned vector quantization, and back propagation for handwritten character recognition , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[23]  Stephen Grossberg,et al.  A fuzzy ARTMAP nonparametric probability estimator for nonstationary pattern recognition problems , 1995, IEEE Trans. Neural Networks.