摘要: This paper introduces the concept of a modular neural network structure, which is capable clustering input patterns through unsupervised learning, and representing self-consistent hierarchy clusters at several levels specificity. In particular, we use ART as building block, name our architecture SMART (for Self-consistent Modular ART). We also show some experimental results for "proof-of-concept" using ARTMAP network, that can be seen an implementation two-level network. >
sci-hub.se 参考文章(4)
Teuvo Kohonen, Self-organized formation of topologically correct feature maps Biological Cybernetics. ,vol. 43, pp. 509- 521 ,(1988) , 10.1007/BF00337288
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
Gail A. Carpenter, Stephen Grossberg, A massively parallel architecture for a self-organizing neural pattern recognition machine Graphical Models \/graphical Models and Image Processing \/computer Vision, Graphics, and Image Processing. ,vol. 37, pp. 54- 115 ,(1987) , 10.1016/S0734-189X(87)80014-2
G.A. Carpenter, S. Grossberg, N. Markuzon, J.H. Reynolds, D.B. Rosen, Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps IEEE Transactions on Neural Networks. ,vol. 3, pp. 698- 713 ,(1992) , 10.1109/72.159059