Informational capacity and recall quality in sparsely encoded Hopfield-like neural network: Analytical approaches and computer simulation

Neural Networks

Volumn 10, Issue 5, 1997, Pages 845-855

  Frolov, Alexander A ^a   Husek, Dusan ^b   Muraviev, Igor P ^a  

^a INSTITUTE OF HIGHER NERVOUS ACTIVITY AND NEUROPHYSIOLOGY   (Russian Federation)

^b INSTITUTE OF COMPUTER SCIENCE   (Czech Republic)

Author keywords

Hopfield like network; Information capacity; Recall quality; Sparse encoding

Indexed keywords

HOPFIELD LIKE NETWORK; REPLICA METHOD (RM); STATISTICAL NEURODYNAMICS;

APPROXIMATION THEORY; CHANNEL CAPACITY; COMPUTER SIMULATION; STATISTICAL METHODS;

NEURAL NETWORKS;

ARTICLE; ARTIFICIAL NEURAL NETWORK; COMPUTER SIMULATION; PRIORITY JOURNAL;

EID: 0031194343     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(96)00122-0     Document Type: Article

References (17)

1. Amari, S. (1989). Characteristics of sparsely encoded associative memory. Neural Networks, 2, 451-457.
2. Amari, S., & Maginu, K. (1988). Statistical neurodynamics of associative memory. Neural Networks, 1, 63-73.
3. Amit, D. J., Gutfreund, H., & Sompolinsky, H. (1987). Statistical mechanics of neural networks near saturation. Annals of Physics, 173, 30-67.
4. Buhmann, J., Divko, R., & Schulten, K. (1989). Associative memory with high information content. Physical Review A, 39, 2689-2692.
5. Frolov, A. A., & Muraviev, I. P. (1993). Informational characteristics of neural networks capable of associative learning based on Hebbian plasticity. Network, 4, 495-536.
6. Frovol, A. A., Mushinsky, A. M., & Tsodyks, M. V. (1991). Imitation model of associative memory as a neuron network with low activity level. Biofizika, 36, 339-343.
7. Gardner, F. (1988). The space of interactions in neural network models. Journal of Physics A, 21, 257-270.
8. Gibson, W. G., & Robinson, J. (1992). Statistical analysis of the dynamics of a sparse associative memory. Neural Networks, 5, 645-661.
9. Hopfield, J. J. (1982). Neural network and physical systems with emergent collective computational abilities. Proceedings of the National Academy of Science USA, 79, 2544-2548.
10. Horner, H. (1989). Neural networks with low levels of activity: Ising vs McCulloch-Pitts neurons. Z Physics B, 75, 133-136.
11. Husek, D., & Frolov, A. A. (1994). Evaluation of the informational capacity of Hopfield network by computer simulation. Neural Network World, 4, 53-65.
12. Kinzel, W. (1985). Learning and pattern recognition in spin glass models. Z Physics B. 60, 205-213.
13. Kohring, G. A. (1990). A high-precision study of the Hopfield model in the phase of broken replica symmetry. Journal of Statistical Physics, 59 (3-4), 1077-1086.
14. Palm, G. (1987). Computing with neural networks. Science, 235, 1227-1228.
15. Perez-Vicente, C. J., & Amit, D. J. (1989). Optimized network for sparsely coded patterns. Journal of Physics A: Math. Gen., 22, 559-569.
16. Tsodyks, M. V., & Fiegelman, M. V. (1988). The enhanced storage capacity in neural network with low activity level. Europhysical Letters, 6, 101-105.
17. Weisbuch, G., & Fogelman-Soulie, S. (1985). Scaling laws for the attractors of Hopfield networks. Lettre au Journal de Physique, 44, 623-630.