Stochastic learning in a neural network with adapting synapses

Physical Review E - Statistical Physics, Plasmas, Fluids, and Related Interdisciplinary Topics

Volumn 56, Issue 4, 1997, Pages 4567-4573

  Lattanzi, G ^a   Nardulli, G ^a   Pasquariello, G ^b   Stramaglia, S ^b  

^a INFN SEZIONE DI BARI   (Italy)

^b CNR   (Italy)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 0006986204     PISSN: 1063651X     EISSN: None     Source Type: Journal    
DOI: 10.1103/PhysRevE.56.4567     Document Type: Article

References (19)

1. D. J. Amit, Modeling Brain Function (Cambridge University Press, 1989);
2. J. Hertz, A. Krogh, and R. Palmer, Introduction to the Theory of Neural Computation (Santa Fe Institute, Santa Fe, 1990).
3. F. E. Bloom, A. Lazerson, and L. Hofstadter, Brain, Mind and Behavior (W.H. Freeman, San Francisco, 1985).
4. S. Shinomoto, J. Phys. A 20, L1305 (1987).JPHAC5
5. D. W. Dong and J. J. Hopfield, Network 3, 267 (1992).NWRKEA
6. R. D’Autilia and F. Guerra, in Representations of Musical Signals, edited by G. De Poli, A. Piccialli, and C. Roads (MIT Press, Cambridge, 1991).
7. J. J. Hopfield, Proc. Natl. Acad. Sci. USA 79, 2554(1982).PNASA6
8. R. W. Penney, A. C. C. Coolen, and D. Sherrington, J. Phys. A 26, 3681 (1993); JPHAC5
9. A. C. C. Coolen, R. W. Penney, and D. Sherrington, Phys. Rev. B 48, 16 116 (1993); PRBMDO
10. R. W. Penney and D. Sherrington, J. Phys. A 27, 4027 (1994).JPHAC5
11. V. Dotsenko, S. Franz, and M. Mézard, J. Phys. A 27, 2351 (1994).JPHAC5
12. N. Caticha, J. Phys. A 27, 5501 (1994).JPHAC5
13. M. Tsodyks, Mod. Phys. Lett. B 4, 713 (1990).MPLBET
14. D. J. Amit and S. Fusi, Neural Comput. 6, 957 (1994).NEUCEB
15. B. Derrida, E. Gardner, and A. Zippelius, Europhys. Lett. 4, 167 (1987).EULEEJ
16. A. C. C. Coolen and D. Sherrington, Phys. Rev. Lett. 71, 3886 (1993).PRLTAO
17. J. P. Nadal, G. Toulouse, J. P. Changeus, and S. Dehaene, Europhys. Lett. 10, 535 (1986).EULEEJ
18. G. Parisi, J. Phys. A 15, L617 (1986).JPHAC5
19. a fully connected network is considered and the capacity is proportional to (Formula presented), where (Formula presented) is the number of neurons in the network. The same analysis holds in a diluted network where each neuron is connected to (Formula presented) random input neurons and the capacity in this case is proportional to (Formula presented).