Gaussian ARTMAP: a neural network for fast incremental learning of noisy multidimensional maps
DOI: 10.1016/0893-6080(95)00115-8
关键词: Benchmark (computing) 、 Computer science 、 Radial basis function 、 Artificial intelligence 、 Fuzzy logic 、 Incremental learning 、 Adaptive resonance theory 、 Gaussian 、 Normalization (statistics) 、 Discriminant function analysis 、 Artificial neural network 、 Pattern recognition (psychology) 、 Pattern recognition 、 Separable space 、 Supervised learning
摘要: Abstract A new neural network architecture for incremental supervised learning of analog multidimensional maps is introduced. The architecture, called Gaussian ARTMAP, a synthesis classifier and an adaptive resonance theory (ART) network, achieved by defining the ART choice function as discriminant with separable distributions, match same, but distributions normalized to unit height. While ARTMAP retains attractive parallel computing fast properties fuzzy it learns more efficient internal representation mapping while being resistant noise than on number benchmark databases. SSeveral simulations are presented which demonstrate that consistently obtains better trade-off classification rate categories ARTMAP. Results vowel problem also outperforms many other classifiers. Copyright © 1996 Elsevier Science Ltd
elsevier.com
sci-hub.se 参考文章(25)
David Lowe, David S. Broomhead, Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks Complex Systems. ,vol. 2, pp. 321- 355 ,(1988)
Stephen Grossberg, Stephen Grossberg, A Theory of Human Memory: Self-Organization and Performance of Sensory-Motor Codes, Maps, and Plans Progress in Theoretical Biology#R##N#Volume 5. pp. 498- 639 ,(1982) , 10.1007/978-94-009-7758-7_13
M. J. D. Powell, Radial basis functions for multivariable interpolation: a review Algorithms for approximation. pp. 143- 167 ,(1987)
Tomaso Poggio, Federico Girosi, A Theory of Networks for Approximation and Learning Massachusetts Institute of Technology. ,(1989)
S. Grossberg, Adaptive pattern classification and universal recoding: I. Parallel development and coding of neural feature detectors Biological Cybernetics. ,vol. 23, pp. 121- 134 ,(1976) , 10.1007/BF00344744
M. G. Cox, J. C. Mason, Algorithms for Approximation ,(1987)
Teuvo Kohonen, Self-Organization and Associative Memory ,(1984)
Bernd Fritzke, Growing cell structures—a self-organizing network for unsupervised and supervised learning Neural Networks. ,vol. 7, pp. 1441- 1460 ,(1994) , 10.1016/0893-6080(94)90091-4
Gail A. Carpenter, Stephen Grossberg, David 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) , 10.1016/0893-6080(91)90056-B
Gail A. Carpenter, Stephen Grossberg, John 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) , 10.1016/0893-6080(91)90012-T