Geodesic
A recurrent method for effective learning of certain algebraic networks of $\Sigma\Pi$-neurons and $\Sigma\Pi$-neuromodules
Žurnal vyčislitelʹnoj matematiki i matematičeskoj fiziki, Tome 43 (2003) no. 8, pp. 1260-1272 
Z. M. Shibzukhov. A recurrent method for effective learning of certain algebraic networks of $\Sigma\Pi$-neurons and $\Sigma\Pi$-neuromodules. Žurnal vyčislitelʹnoj matematiki i matematičeskoj fiziki, Tome 43 (2003) no. 8, pp. 1260-1272. http://geodesic.mathdoc.fr/item/ZVMMF_2003_43_8_a11/
@article{ZVMMF_2003_43_8_a11,
     author = {Z. M. Shibzukhov},
     title = {A recurrent method for effective learning of certain algebraic networks of $\Sigma\Pi$-neurons and $\Sigma\Pi$-neuromodules},
     journal = {\v{Z}urnal vy\v{c}islitelʹnoj matematiki i matemati\v{c}eskoj fiziki},
     pages = {1260--1272},
     year = {2003},
     volume = {43},
     number = {8},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/ZVMMF_2003_43_8_a11/}
}
TY  - JOUR
AU  - Z. M. Shibzukhov
TI  - A recurrent method for effective learning of certain algebraic networks of $\Sigma\Pi$-neurons and $\Sigma\Pi$-neuromodules
JO  - Žurnal vyčislitelʹnoj matematiki i matematičeskoj fiziki
PY  - 2003
SP  - 1260
EP  - 1272
VL  - 43
IS  - 8
UR  - http://geodesic.mathdoc.fr/item/ZVMMF_2003_43_8_a11/
LA  - ru
ID  - ZVMMF_2003_43_8_a11
ER  - 
%0 Journal Article
%A Z. M. Shibzukhov
%T A recurrent method for effective learning of certain algebraic networks of $\Sigma\Pi$-neurons and $\Sigma\Pi$-neuromodules
%J Žurnal vyčislitelʹnoj matematiki i matematičeskoj fiziki
%D 2003
%P 1260-1272
%V 43
%N 8
%U http://geodesic.mathdoc.fr/item/ZVMMF_2003_43_8_a11/
%G ru
%F ZVMMF_2003_43_8_a11

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

[1] Pshibikhov A. V., Timofeev A. V., “Algoritm obucheniya i minimizatsii slozhnosti polinomialnykh raspoznayuschikh sistem”, Izv. AN SSSR. Tekhn. kibernetika, 1974, no. 5, 214–217

[2] Shibzukhov Z. M., “Neiroprotsessornye elementy polinomialnogo tipa iskusstvennykh neironnykh setei”, Dokl. Adygskoi AN, 4:1 (1999), 64–68

[3] Mel B. W., Conectionist robot motion planing, Acad. Press, New York, 1990

[4] Ballard D. H., Feldman J. A., “Connectionist models and their properties”, Cognitive Sci., 1982, no. 6, 205–254

[5] Gurney K. N., “Training nets of hardware relaizable sigma-pi units”, Neural Networks, 1992, no. 5, 289–303 | DOI

[6] Avsarkisyan G. S., “Rekurrentnye polinomialnye formy chastichnykh bulevykh funktsii”, Izv. AN SSSR. Tekhn. kibernetika, 1987, no. 4, 131–135 | MR

[7] Timofeev A. V., “Metody sinteza diofantovykh neirosetei minimalnoi slozhnosti”, Dokl. RAN, 345:1 (1995), 32–35 | MR | Zbl

[8] Shibzukhov Z. M., “Rekurrentnaya skhema postroeniya kortezhei mnogoznachnykh funktsii i obucheniya neironnykh setei”, Dokl. Adygskoi AN, 3:2 (1998), 45–51

[9] Shibzoukhov Z. M., “Constructive training of Boolean-valued neural networks of recognition and classification of the polynomial type”, Pattern Recognition and Image Analys., 11:1 (2001), 95–96

[10] Shibzukhov Z. M., “Rekurrentnye metody dlya konstruktivnogo obucheniya neitronnykh setei iz logiko-arifmeticheskikh sigma-arifmeticheskikh sigma-pi neironov”, Neirokompyutery: razrabotka i primenenie, 2002, no. 5–6, 50–57

[11] Gurevich I. B., Zhuravlev Yu. I., “Raspoznavanie obrazov i obrabotka izobrazhenii”, Iskusstvennyi intellekt, v. 2, kn. 2, Radio i svyaz, M., 1990

[12] Zhuravlev Yu. I., Problemy kibernetiki, 33, Nauka, M., 1978, 5–68