Skip to Main Content

Access Provided by Xinjiang University

Physical Review E

Access by Xinjiang University

Pattern reconstruction and sequence processing in feed-forward layered neural networks near saturation

F. L. Metz and W. K. Theumann

Instituto de Física, Universidade Federal do Rio Grande do Sul, Caixa Postal 15051, 91501-970 Porto Alegre, Brazil

Phys. Rev. E 72, 021908 – Published 23 August, 2005

DOI: https://doi.org/10.1103/PhysRevE.72.021908

Abstract

The dynamics and the stationary states for the competition between pattern reconstruction and asymmetric sequence processing are studied here in an exactly solvable feed-forward layered neural network model of binary units and patterns near saturation. Earlier work by Coolen and Sherrington on a parallel dynamics far from saturation is extended here to account for finite stochastic noise due to a Hebbian and a sequential learning rule. Phase diagrams are obtained with stationary states and quasiperiodic nonstationary solutions. The relevant dependence of these diagrams and of the quasiperiodic solutions on the stochastic noise and on initial inputs for the overlaps is explicitly discussed.

Article Text

References (31)

J. J. Hopfield, Proc. Natl. Acad. Sci. U.S.A. 79, 2554 (1982); 81, 3088 (1984).
H. Sompolinsky and I. Kanter, Phys. Rev. Lett. 57, 2861 (1986).
S. Amari and K. Maginu, Neural Networks 1, 63 (1988).
A. V. M. Herz, Z. Li, and J. L. van Hemmen, Phys. Rev. Lett. 66, 1370 (1991).
K. Bauer and U. Krey, Z. Phys. B: Condens. Matter 84, 131 (1991).
G. Mato and N. Parga, Z. Phys. B: Condens. Matter 84, 483 (1991).
R. Kühn and J. L. van Hemmen, Models of Neural Networks I, edited by E. Domany, J. L. van Hemmen, and K. Schulten (Springer-Verlag, Berlin, 1991), p. 213.
H. Rieger, M. Schreckenberg, and J. Zittartz, J. Phys. A 21, L263 (1988); Z. Phys. B: Condens. Matter 72, 523 (1988).
A. C. C. Coolen and D. Sherrington, Phys. Rev. Lett. 71, 3886 (1993); Phys. Rev. E 49, 1921 (1994).
S. N. Laughton and A. C. C. Coolen, Phys. Rev. E 51, 2581 (1995).
M. Okada, Neural Networks 9, 1429 (1996).
A. Düring, A. C. C. Coolen, and D. Sherrington, J. Phys. A 31, 8607 (1998).
Y. Miyashita and H. S. Chang, Nature (London) 331, 68 (1988).
Y. Miyashita, Nature (London) 335, 817 (1988).
M. Griniasty, M. V. Tsodyks, and D. J. Amit, Neural Comput. 5, 1 (1993).
N. Brunel, Network Comput. Neural Syst. 5, 449 (1994).
L. F. Cugliandolo, Neural Comput. 6, 220 (1994).
L. F. Cugliandolo and M. V. Tsodyks, J. Phys. A 27, 741 (1994).
T. Uezu, A. Hirano, and M. Okada, J. Phys. Soc. Jpn. 73, 867 (2004).
D. J. Amit, H. Gutfreund, and H. Sompolinsky, Ann. Phys. 173, 30 (1987).
A. C. C. Coolen and D. Sherrington, J. Phys. A 25, 5493 (1992).
W. Whyte, D. Sherrington, and A. C. C. Coolen, J. Phys. A 28, 3421 (1995).
K. Kitano and T. Aoyagi, J. Phys. A 31, L613 (1998).
M. Kawamura and M. Okada, J. Phys. A 35, 253 (2002).
W. K. Theumann, Physica B 328, 1 (2003).
K. Mimura, M. Kawamura, and M. Okada, J. Phys. A 37, 6437 (2004).
E. Domany, W. Kinzel, and R. Meir, J. Phys. A 22, 2081 (1989); R. Meir and E. Domany, Phys. Rev. Lett. 59, 359 (1987).
D. J. Amit, H. Gutfreund, and H. Sompolinsky, Phys. Rev. A 35, 2293 (1987).
J-P. Eckmann and D. Ruelle, Rev. Mod. Phys. 57, 617 (1985).
B. G. Nielsen, Neural Comput. 14, 189 (2003).
Z. Li and P. Dayan, Network Comput. Neural Syst. 10, 59 (1999).