Geodesic
High-symmetry Hopfield-type neural networks
Teoretičeskaâ i matematičeskaâ fizika, Tome 118 (1999) no. 1, pp. 133-158 Cet article a éte moissonné depuis la source Math-Net.Ru

Voir la notice de l'article

We study the set of fixed points of a Hopfield-type neural network with a connection matrix constructed from a high-symmetry set of memorized patterns using the Hebb rule. The memorized patterns depending on an external parameter are interpreted as distorted copies of a vector standard to be learned by the network. The dependence of the fixed-point set of the network on the distortion parameter is described analytically. The investigation results are interpreted in terms of neural networks and the Ising model. 
@article{TMF_1999_118_1_a9,
     author = {L. B. Litinskii},
     title = {High-symmetry {Hopfield-type} neural networks},
     journal = {Teoreti\v{c}eska\^a i matemati\v{c}eska\^a fizika},
     pages = {133--158},
     year = {1999},
     volume = {118},
     number = {1},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/TMF_1999_118_1_a9/}
}
TY  - JOUR
AU  - L. B. Litinskii
TI  - High-symmetry Hopfield-type neural networks
JO  - Teoretičeskaâ i matematičeskaâ fizika
PY  - 1999
SP  - 133
EP  - 158
VL  - 118
IS  - 1
UR  - http://geodesic.mathdoc.fr/item/TMF_1999_118_1_a9/
LA  - ru
ID  - TMF_1999_118_1_a9
ER  - 
%0 Journal Article
%A L. B. Litinskii
%T High-symmetry Hopfield-type neural networks
%J Teoretičeskaâ i matematičeskaâ fizika
%D 1999
%P 133-158
%V 118
%N 1
%U http://geodesic.mathdoc.fr/item/TMF_1999_118_1_a9/
%G ru
%F TMF_1999_118_1_a9
L. B. Litinskii. High-symmetry Hopfield-type neural networks. Teoretičeskaâ i matematičeskaâ fizika, Tome 118 (1999) no. 1, pp. 133-158. http://geodesic.mathdoc.fr/item/TMF_1999_118_1_a9/

[1] E. Domany, J. L. van Hemmen, K. Schulten (eds.), Models of neural networks, Springer-Verlag, Berlin, 1991 | MR

[2] U. Blasum, W. Hochstattler, C. Moll, H. Rieger, Using network-flow techniques to solve an optimization problem from surface-physics, , 1996 E-print Cond-mat/9604052 | MR

[3] N. Sourlas, Europhys. Lett., 25 (1994), 159 | DOI | MR

[4] G. Parisi, Attractor Neural Networks, , 1994 E-print Cond-mat/9412030 | MR

[5] E. M. Braverman, I. B. Muchnik, Strukturnye metody obrabotki empiricheskikh dannykh, Nauka, M., 1983 | MR | Zbl

[6] L. B. Litinskii, Matematicheskoe modelirovanie, 8:11 (1996), 119–127 | MR | Zbl

[7] L. B. Litinsky, Energy functional and fixed points of neural network, , 1997 E-print Cond-mat/9706280

[8] J. J. Hopfield, Proc. Nat. Acad. Sci. USA, 79 (1982), 2554 | DOI | MR

[9] P. Baldi, IEEE Trans. on Inform. Theory, 34 (1988), 523 | DOI | MR | Zbl

[10] T. L. H. Watkin, A. Rau, M. Biehl, Rev. Mod. Phys., 65 (1993), 499 | DOI | MR

[11] B. Muller, J. Reinhardt, M. T. Strikland, Neural Networks. An Introduction, Sec. edit., Springer-Verlag, Berlin, 1995 | MR | Zbl

[12] S. Diderich, M. Opper, Phys. Rev. Lett., 58 (1987), 949 | DOI | MR

[13] L. B. Litinskii, TMF, 101 (1994), 467 | MR | Zbl

[14] A. A. Vedenov, A. A. Ezhov et al., “Structure of patterns in associative memory models”, Neural Networks–Theory and Architecture, eds. A. V. Holden, V. I. Kryukov, Manch. Univ. Press, Manchester, 1991, 169 | MR

[15] L. B. Litinskii, Uchet magnitnogo polya dlya modeli Izinga s vysokosimmetrichnoi matritsei svyazei, Gotovitsya k publikatsii

[16] L. B. Litinsky, Solid State Commun., 79 (1991), 879 | DOI