Geodesic
About the Mechanism of Neural Network as Adaptive System Training
Matematičeskaâ biologiâ i bioinformatika, Tome 8 (2013) no. 1, pp. 12-20.

Voir la notice de l'article provenant de la source Math-Net.Ru

The dynamics of error learning neural networks, obtained under identical conditions of the problem being solved and the parameters of networks, but with different initial conditions of the network are analyzed. And also a possible theoretical model of a single mechanism for training of artificial and natural adaptive systems is attempted to offer. 
@article{MBB_2013_8_1_a5,
     author = {V. A. Lorents and V. L. Gavrikov and R. G. Khlebopros},
     title = {About the {Mechanism} of {Neural} {Network} as {Adaptive} {System} {Training}},
     journal = {Matemati\v{c}eska\^a biologi\^a i bioinformatika},
     pages = {12--20},
     publisher = {mathdoc},
     volume = {8},
     number = {1},
     year = {2013},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/MBB_2013_8_1_a5/}
}
TY  - JOUR
AU  - V. A. Lorents
AU  - V. L. Gavrikov
AU  - R. G. Khlebopros
TI  - About the Mechanism of Neural Network as Adaptive System Training
JO  - Matematičeskaâ biologiâ i bioinformatika
PY  - 2013
SP  - 12
EP  - 20
VL  - 8
IS  - 1
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/MBB_2013_8_1_a5/
LA  - ru
ID  - MBB_2013_8_1_a5
ER  - 
%0 Journal Article
%A V. A. Lorents
%A V. L. Gavrikov
%A R. G. Khlebopros
%T About the Mechanism of Neural Network as Adaptive System Training
%J Matematičeskaâ biologiâ i bioinformatika
%D 2013
%P 12-20
%V 8
%N 1
%I mathdoc
%U http://geodesic.mathdoc.fr/item/MBB_2013_8_1_a5/
%G ru
%F MBB_2013_8_1_a5
V. A. Lorents; V. L. Gavrikov; R. G. Khlebopros. About the Mechanism of Neural Network as Adaptive System Training. Matematičeskaâ biologiâ i bioinformatika, Tome 8 (2013) no. 1, pp. 12-20. http://geodesic.mathdoc.fr/item/MBB_2013_8_1_a5/

[1] Gavrikov V. L., Khlebopros R. G., “Dve dinamicheskie modeli naucheniya tipa «koshka Torndaika»”, Vestnik Krasnoyarskogo gosudarstvennogo pedagogicheskogo universiteta im. V. P. Astafeva, 2 (2009), 47–55

[2] Lin C. S., Chang C. C., Chiu J. S., Lee Y. W., Lin J. A., Mok M. S., Chiu H. W., Li Y. C., “Application of an Artificial Neural Network to Predict Postinduction Hypotension During General Anesthesia”, Medical Decision Making, 31:2 (2011), 308–314 | DOI

[3] Reznikova Zh. I., Intellekt i yazyk zhivotnykh i cheloveka. Osnovy kognitivnoi etologii, uchebnoe posobie dlya vuzov, IKTs «Akademkniga», M., 2005, 518 pp.

[4] Fomin V. N., Fradkov A. L., Yakubovich V. A., Adaptivnoe upravlenie dinamicheskimi ob'ektami, Nauka, M., 1981 | MR

[5] Bartsev S. I., Bartseva O. D., Evristicheskie neirosetevye modeli v biofizike: prilozhenie k probleme strukturno-funktsionalnogo sootvetstviya, monografiya, Izd-vo Sibirskogo federalnogo universiteta, Krasnoyarsk, 2010, 115 pp.

[6] Bartsev S. I., Okhonin V. A., Adaptivnye seti obrabotki informatsii, preprint No 59B, IF SO AN SSSR, Krasnoyarsk, 1986, 20 pp.

[7] Gavrikov V. L., Khlebopros R. G., “Kontinualnost tipov naucheniya: dinamicheskoe modelirovanie na osnove teorii katastrof”, Vestnik Tomskogo gosudarstvennogo universiteta, 331 (2010), 163–170

[8] Lorents V. A., Gavrikov V. L., Khlebopros R. G., “Analiz obucheniya neironnoi seti zadacham, soderzhaschim skrytuyu zakonomernost”, Vestnik KrasGAU, 5 (2012), 88–92

[9] Gorban A. N., Obuchenie neironnykh setei, ParaGraph, M., 1990, 160 pp.

[10] Noskov M. V., Simonov K. V., Schemel A. L., “Nelineinaya mnogoparametricheskaya regressiya dannykh nablyudenii”, Voprosy matematicheskogo analiza, 7, ITsP KGTU, 2003, 103–120