Geodesic
Hopfield Model with a Dynamic Threshold
Teoretičeskaâ i matematičeskaâ fizika, Tome 130 (2002) no. 1, pp. 159-176
Cet article a éte moissonné depuis la source Math-Net.Ru

Voir la notice de l'article

We study the dependence of the result of learning on the dynamic threshold $H$ in the Hopfield neural network model. We obtain rigorous results relating the quality of learning to the threshold. 
@article{TMF_2002_130_1_a10,
     author = {L. B. Litinskii},
     title = {Hopfield {Model} with {a~Dynamic} {Threshold}},
     journal = {Teoreti\v{c}eska\^a i matemati\v{c}eska\^a fizika},
     pages = {159--176},
     year = {2002},
     volume = {130},
     number = {1},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/TMF_2002_130_1_a10/}
}
TY  - JOUR
AU  - L. B. Litinskii
TI  - Hopfield Model with a Dynamic Threshold
JO  - Teoretičeskaâ i matematičeskaâ fizika
PY  - 2002
SP  - 159
EP  - 176
VL  - 130
IS  - 1
UR  - http://geodesic.mathdoc.fr/item/TMF_2002_130_1_a10/
LA  - ru
ID  - TMF_2002_130_1_a10
ER  - 
%0 Journal Article
%A L. B. Litinskii
%T Hopfield Model with a Dynamic Threshold
%J Teoretičeskaâ i matematičeskaâ fizika
%D 2002
%P 159-176
%V 130
%N 1
%U http://geodesic.mathdoc.fr/item/TMF_2002_130_1_a10/
%G ru
%F TMF_2002_130_1_a10
L. B. Litinskii. Hopfield Model with a Dynamic Threshold. Teoretičeskaâ i matematičeskaâ fizika, Tome 130 (2002) no. 1, pp. 159-176. http://geodesic.mathdoc.fr/item/TMF_2002_130_1_a10/

[1] L. B. Litinskii, TMF, 118:1 (1999), 133 | DOI | MR | Zbl

[2] B. M. Forrest, D. J. Wallace, “Storage capacity and learning in Ising-spin neural networks”, Models of Neural Networks, eds. E. Domany, J. L. van Hemmen, K. Schulten, Springer, Berlin, 1991, 121 | DOI | MR

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

[4] A. A. Ezhov, S. A. Shumskii, Neirokompyuting i ego prilozheniya v ekonomike i biznese, MIFI, M., 1998

[5] R. Bekster, Tochno reshaemye modeli v statisticheskoi mekhanike, Mir, M., 1985 | MR

[6] A. S. Andreenko, S. A. Nikitin, UFN, 167 (1997), 605 | DOI

[7] J. Hertz, A. Krogh, R. Palmer, Introduction to the Theory of Neural Computation, Addison-Wesley, Massachusetts, 1991 | MR

[8] M. Tsoydyks, Mod. Phys. Lett. B, 3 (1989), 555 | DOI

[9] O. Kufudaki, J. Horejs, “Associative neural networks with threshold-controlled attention”, Neurocomputers and Attention. V. II. Connectionism and Neurocomputers, eds. A. V. Holden, V. I. Kryukov, Manchester Univ. Press, Manchester, 1991, 567 | MR

[10] B. Willshow, Network, 4 (1993), 441 | DOI

[11] W. L. Dunin-Barkovski, N. B. Osovets, Neural Processing Lett., 2 (1995), 28 | DOI

[12] S. Galam, Physica A, 238 (1997), 66 | DOI

[13] R. Axelrod, The Complexity of Cooperation, Princeton Univ. Press, Princeton, 1997

[14] K. Kasperski, J. A. Holyst, Physica A, 287 (2000), 631 | DOI

[15] D. Chowdhury, D. Staufer, Europ. Phys. J. B, 8 (1999), 477 | DOI

[16] T. Kaizoji, Physica A, 287 (2000), 493 | DOI

[17] R. N. Mantegna, H. E. Stanley, An Introduction to Econophysics, Cambridge Univ. Press, Cambridge, 2000 | MR

[18] http://www.unifr.ch/econophysics