Binary factorization in hopfield-like neural networks: Single-step approximation and computer simulations

Neural Network World

Volumn 14, Issue 2, 2004, Pages 139-152

  Frolov, A A ^a   Sirota, A M ^b   Husek D ^c   Muraviev, I P ^a   Polyakov, P A ^d  

^a RUSSIAN ACADEMY OF SCIENCES   (Russian Federation)

^b RUTGERS UNIVERSITY   (United States)

^c INSTITUTE OF COMPUTER SCIENCE   (Czech Republic)

^d MOSCOW INSTITUTE OF PHYSICS AND TECHNOLOGY   (Russian Federation)

Author keywords

Attraction basins; Brain functions modeling; Feature extraction; Hebbian learning; Neurodynamics simulation; Neuroscience; Nonlinear binary factor analysis; Recurrent neural network; Single Step approximation; Unsupervised learning

Indexed keywords

BRAIN FUNCTIONS MODELING; NEURODYNAMICS LEARNING; NONLINEAR BINARY FACTOR ANALYSIS; SINGLE STEP APPROXIMATION;

APPROXIMATION THEORY; COMPUTER SIMULATION; FEATURE EXTRACTION; LEARNING SYSTEMS; NEUROLOGY; PRINCIPAL COMPONENT ANALYSIS; PROBLEM SOLVING;

RECURRENT NEURAL NETWORKS;

EID: 2342557999     PISSN: 12100552     EISSN: None     Source Type: Journal    
DOI: None     Document Type: Article

References (16)

1. Amari S., Maginu K.: Statistical neurodynamics of associative memory. Neural Networks, 1, 1988, pp. 63-73.
2. Amit D. J., Gutfreund H., Sompolinsky H.: Statistical mechanics of neural networks near saturation. Annal of Physics, 173, 1987, pp. 30-67.
3. Bucingham J., Willshaw D.: On setting unit thresholds in an incompletely connected associative net. Network, 4, 1993, pp. 441-459.
4. Buhmann J., Divko R., Schulten K.: Associative memory with high information content. Physical Review A, 39, 1989, pp. 2689-2692.
5. Buzsaki G.: Two-stage model of memory trace formation: a role of "noisy" brain states. Neuroscience, 31, 3, 1989, pp. 551-570.
6. Buzsaki G.: The hippocampo-neocortical dialog. Cereb. Cortex, 6, 2, 1996, pp. 81-92.
7. Goles-Chacc E., Fogelman-Soulie F., Pellegrin D.: Decreasing energy functions as a tool for studying threshold networks. Discrete mathematics, 12, 1985, pp. 261-277.
8. Frolov A. A., Húsek D., Muraviev I. P.: Informational capacity and recall quality in sparsely encoded Hopfield-like neural network: Analytical approaches and computer simulation. Neural Networks, 10, 1997, pp. 845-855.
9. Fu K. S., Rosenfeld A.: Pattern recognition and computer vision. Computer, 17, 1984, pp. 274-282.
10. Hopfield J. J.: Neural network and physical systems with emergent collective computational abilities. Proceedings of the National Academy of Science USA, 79, 1982, pp. 2544-2548.
11. Kinzel W.: Learning and pattern recognition in spin glass models. Z Physik B, 60, 1985, pp. 205-213.
12. Kohring G. A.: A high-precision study of the Hopfield model in the phase of broken replica symmetry. Journal of Statistical Physics, 59, 1990, pp. 1077-1086.
13. Marr D.: A theory of cerebral neocortex. Proc. Roy. Soc. London, B 176, 1970, pp. 163-234.
14. Marr D.: Simple memory: a theory for archicortex. Phil. Trans. Roy. Soc. London, B 262, 1971, pp. 24-81.
15. Oja E., Ogawa H., Wangviwattana J.: Learning in nonlinear constrained Hebbian network. Proc. ICANN-91, Espoo, Finland, 1991, pp. 385-390.
16. Rolls R. T.: The representation and storage of information in neural networks in the primate cerebral cortex and hippocampus. In: R. Durbin, C. Miall and G. Mitchison, editors, The Computing Neuron. Addison-Weley, Reading, MA, 1989.