Variational approach to unsupervised learning algorithms of neural networks

Neural Networks

Volumn 10, Issue 2, 1997, Pages 273-289

  Likhovidov, Victor ^a  

^a NONE   (Russian Federation)

Author keywords

adaptive Hebb Hopfield networks; convergence; Grossberg networks; Kohonen networks; mean risk funtional; neural networks; optimum conditions; stochastic approximation; unsupervised learning

Indexed keywords

APPROXIMATION THEORY; CONVERGENCE OF NUMERICAL METHODS; DATA PROCESSING; NEURAL NETWORKS; PATTERN RECOGNITION;

ADAPTIVE HEBB-HOPFIELD NETWORKS; GROSSBERG NETWORKS; KOHONEN NETWORKS; MEAN RISK FUNCTIONAL; OPTIMUM CONDITIONS; STOCHASTIC APPROXIMATION; UNSUPERVISED LEARNING ALGORITHMS;

LEARNING ALGORITHMS;

ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; LEARNING; PRIORITY JOURNAL;

EID: 0031104848     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(96)00051-2     Document Type: Article

References (32)

1. Aizerman, M. A., Braverman, E. M., & Rosonoer, L. I. (1970). Method of potential functions in the theory of machine learning. Moscow (in Russian).
2. Bauer, H.-U., & Pawelzik, K. R. (1992). Quantifying the neighborhood preservation of self-organizing feature maps. IEEE Transactions on Neural Networks, 3(4), July, 570-578.
3. Burago, V. A., & Likhovidov, V. N. (1990). Calculation of the second variation of integral over multidimensional domain. Application to pattern recognition. In Problems of modeling and control (pp. 57-71). Vladivostok: Far-Eastern State University Publishers (in Russian).
4. Burke, L. I. (1991). Clustering characterization of adaptive resonans. Neural Networks, 4, 485-491.
5. Carpenter, G. A. (1989). Neural network models for pattern recognition and associative memory. Neural Networks, 22, 243-257.
6. Carpenter, G. A., & Grossberg, S. (1987) ART-2: Self-organization of stable category recognition codes for analog input patterns. Applied Optics, 26 (23), 4919-4930.
7. Clark, D. M., & Ravishankar, K. (1990). A convergence theorem for Grossberg learning. Neural Networks, 3, 87-92.
8. Duda, R. O., & Hart, P. E. (1973). Pattern classification and scene analysis. New York: John Wiley.
9. Duran, B. S., & Odell, P. L. (1974). Cluster analysis. A survey. Berlin: Springer-Verlag.
10. Fogelman Soulie, F., Meja, C., Goles, E., & Martinez, S. (1989). Energy functions in neural networks with continuous local functions. Complex Systems, 3, 269-293.
11. Fomin, V. N. (1976). Mathematical theory of learning recognizing systems. Leningrad: Leningrad University Publishers (in Russian).
12. Fomin, V. N. (1984). Recurrent estimation and adaptive filtering. Moscow (in Russian).
13. Fromm, F. R., & Northouse, R. A. (1976) Class: a nonparametric clustering algorithm. Pattern Recognition, 8, 107-114.
14. Fukunaga, K. (1972). Introduction to statistical pattern recognition. New York: Academic Press.
15. Grossberg, S. (1976). Adaptive pattern classification and universal recoding: I. Parallel development and coding of neural feature detectors. Biological Cybernetics, 23, 121-134.
16. Hecht-Nielsen, R. (1987). Counter-propagation networks. Applied Optics, 26, 4979-4984.
17. Hopfield, J. J. (1982). Neural networks and physical systems with emergent collective computational abilities. Proceedings of the National Academy of Sciences USA, 79, 2554-2558.
18. Hopfield, J. J. (1984). Neurons with graded response have collective computational properties like those of two-state neurons. Proceedings of the National Academy of Sciences USA, 81, 3088-3092.
19. Jacuna, G. M., & Malaret, E. R. (1989). Classification performance of a Hopfield neural network based on a Hebbian-like learning rule. IEEE Transactions on Information Theory, 35, 263-280.
20. Kamgar-Parsie, B., & Kamgar-Parsie, B. (1990). Simultaneous fitting of several planes to point sets using neural networks. Computer Vision, Graphics and Image Processing, 52, 341-359.
21. Kohonen, T. (1982). Self-organized formation of topologically correct feature maps. Biological Cybernetics, 43, 59-69.
22. Li, X., Gasteiger, I., & Zupan, I. (1993). On the topology distortion in self-organizing feature maps. Biological Cybernetics, 70, 189-198.
23. Likhovidov, V. N., & Fomin, V. N. (1981). A mathematical statement of the problem of pattern classification. Vestnik Leningrad University, 9, 287-296.
24. Likhovidov, V. N., Solonin, A. S., & Fomin, V. N. (1978). On the convergence of recurrent algorithm in the unsupervised learning problem. Vestnik Leningrad University, 13, 138-140 (in Russian).
25. Lippman, R. P. (1987). An introduction to computing with neural nets. IEEE ASSP Magazine, 4, April, 4-22.
26. Lippman, R. P. (1989). Pattern classification using neural networks. IEEE Communications Magazine, November, 47-64.
27. MacQueen, I. (1967). Some methods for classifiction and analysis of multivariate observations. In Proceedings 5th Berkeley Symposium on Mathematical Statistics Problems, pp. 281-297.
28. Oja, E., & Karhunen, I. (1983). An analysis of convergence for a learning version of the subspace method. Journal of Mathematical Analysis and Applications, 91, 102-111.
29. Tsypkin, Ya. Z. (1971). Adaptation and learning in automatic systems. New York, London: Academic Press.
30. Urhama, K. (1989). Global stability of some classes of neural networks. Transactions of JEICE, E72, 863-867.
31. Wasan, M. T. (1969). Stochastic approximation. Cambridge: The University Press.
32. Wold, S. (1976). Pattern recognition by means of disjoint principal components models. Pattern Recognition, 8, 127-139.