Geodesic
Forming a~neuronet database for perceptrons structure optimization
Sibirskij žurnal vyčislitelʹnoj matematiki, Tome 8 (2005) no. 1, pp. 43-55.

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

Results of the solution of a variety of neuronet approximations of different topology functions are used for formation of a training set on which the neuronet database is constructed for the perceptrons structure optimization. 
@article{SJVM_2005_8_1_a4,
     author = {A. V. Kretinin},
     title = {Forming a~neuronet database for perceptrons structure optimization},
     journal = {Sibirskij \v{z}urnal vy\v{c}islitelʹnoj matematiki},
     pages = {43--55},
     publisher = {mathdoc},
     volume = {8},
     number = {1},
     year = {2005},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/SJVM_2005_8_1_a4/}
}
TY  - JOUR
AU  - A. V. Kretinin
TI  - Forming a~neuronet database for perceptrons structure optimization
JO  - Sibirskij žurnal vyčislitelʹnoj matematiki
PY  - 2005
SP  - 43
EP  - 55
VL  - 8
IS  - 1
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/SJVM_2005_8_1_a4/
LA  - ru
ID  - SJVM_2005_8_1_a4
ER  - 
%0 Journal Article
%A A. V. Kretinin
%T Forming a~neuronet database for perceptrons structure optimization
%J Sibirskij žurnal vyčislitelʹnoj matematiki
%D 2005
%P 43-55
%V 8
%N 1
%I mathdoc
%U http://geodesic.mathdoc.fr/item/SJVM_2005_8_1_a4/
%G ru
%F SJVM_2005_8_1_a4
A. V. Kretinin. Forming a~neuronet database for perceptrons structure optimization. Sibirskij žurnal vyčislitelʹnoj matematiki, Tome 8 (2005) no. 1, pp. 43-55. http://geodesic.mathdoc.fr/item/SJVM_2005_8_1_a4/

[1] Dyakonov V. B., Matematicheskie pakety rasshireniya MATLAB. Spetsialnyi spravochnik, eds. V. B. Dyakonov, V. A. Kruglov, Piter, SPb., 2001

[2] Neironnye seti, Per. s angl., Goryachaya liniya – Telekom, M., 2000

[3] Voronovskii G. L., Geneticheskie algoritmy, iskusstvennye neironnye seti i problemy virtualnoi realnosti, eds. G. K. Voronovskii, K. V. Makhotilo, S. N. Petrashev, S. A. Sergeev, Osnova, Kharkov, 1997

[4] Nabkhan T. N., Zomaya A., O problemakh sozdaniya neirosetevykh struktur dlya optimizatsii funktsionirovaniya, http://neuroschool.narod.ru/optbpa.pdf

[5] Statnikov R. B., Matusov I. B., Mnogokriterialnoe proektirovanie mashin, Znanie, M., 1989 | MR

[6] Egorov I. N., Kretinin G. V., Matusov I. B., Statnikov R. B., “Zadachi proektirovaniya i mnogokriterialnogo upravleniya reguliruemykh tekhnicheskikh sistem”, Dokl. AN RF, 359:3 (1998), 330–333

[7] Terekhov S. A., Vvedenie v baiesovy seti / Nauchnaya sessiya MIFI-2003, V Vserossiiskaya konferentsiya “Neiroinformatika-2003”: Lektsii po neiroinformatike. Chast 1, MIFI, M., 2003

[8] Shumskii S. A., Baiesova regulyarizatsiya obucheniya / Nauchnaya sessiya MIFI-2003, V Vserossiiskaya konferentsiya “Neiroinformatika-2003”: Lektsii po neiroinformatike. Chast 2, MIFI, M., 2003

[9] Bishop C. M., Neural networks for pattern recognition, Oxford University Press, Oxford, 1995 | MR

[10] Elektronnyi uchebnik po statistike, , Moskva, 1999 http://www.statsoft.ru /home/textbook/default.htm

[11] MacKay D. J. C., “Bayesian Interpolation”, Neural Computation, 4:3 (1992), 415–447 | DOI

[12] Sevastyanov A. A., Kharintsev S. S., Salakhov M. Kh., “Neirosetevaya regulyarizatsiya resheniya obratnykh nekorrektnykh zadach prikladnoi spektroskopii”, Elektronnyi zhurnal “Issledovano v Rossii”

[13] Rumelhart D. E., Hinton G. E., Williams R. J., “Learning representation by back-propagating errors”, Nature, 323 (1986), 533–536 | DOI

[14] Akima H., “A new method of interpolation and smooth curve fitting based on local procedures”, ACM, 17:4 (1970), 589–602 | DOI | Zbl