Geodesic
Some aspects of approximation and interpolation of functions artificial neural networks
Vestnik KRAUNC. Fiziko-matematičeskie nauki, Tome 38 (2022) no. 1, pp. 54-73 Cet article a éte moissonné depuis la source Math-Net.Ru

Voir la notice de l'article

The article deals with the issues of approximation and interpolation of functions f(x) = |x|, f(x) = sin(x), f(x) =1/(1+25x2) with the help of neural networks from those constructed on the basis of the Kolmogorov-Arnold and Tsybenko theorems. problems in training a neural network based on the initialization of weight coefficients in a random way are shown. The possibility of training a neural network to work with a variety is shown.
Keywords: approximation of functions, interpolation of functions, artificial neural networks, Tsybenko's theorem, Kolmogorov-Arnold's theorem. 
@article{VKAM_2022_38_1_a3,
     author = {V. A. Galkin and T. V. Gavrilenko and A. D. Smorodinov},
     title = {Some aspects of approximation and interpolation of functions artificial neural networks},
     journal = {Vestnik KRAUNC. Fiziko-matemati\v{c}eskie nauki},
     pages = {54--73},
     year = {2022},
     volume = {38},
     number = {1},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/VKAM_2022_38_1_a3/}
}
TY  - JOUR
AU  - V. A. Galkin
AU  - T. V. Gavrilenko
AU  - A. D. Smorodinov
TI  - Some aspects of approximation and interpolation of functions artificial neural networks
JO  - Vestnik KRAUNC. Fiziko-matematičeskie nauki
PY  - 2022
SP  - 54
EP  - 73
VL  - 38
IS  - 1
UR  - http://geodesic.mathdoc.fr/item/VKAM_2022_38_1_a3/
LA  - ru
ID  - VKAM_2022_38_1_a3
ER  - 
%0 Journal Article
%A V. A. Galkin
%A T. V. Gavrilenko
%A A. D. Smorodinov
%T Some aspects of approximation and interpolation of functions artificial neural networks
%J Vestnik KRAUNC. Fiziko-matematičeskie nauki
%D 2022
%P 54-73
%V 38
%N 1
%U http://geodesic.mathdoc.fr/item/VKAM_2022_38_1_a3/
%G ru
%F VKAM_2022_38_1_a3
V. A. Galkin; T. V. Gavrilenko; A. D. Smorodinov. Some aspects of approximation and interpolation of functions artificial neural networks. Vestnik KRAUNC. Fiziko-matematičeskie nauki, Tome 38 (2022) no. 1, pp. 54-73. http://geodesic.mathdoc.fr/item/VKAM_2022_38_1_a3/

[1] Braun J., Griebel M., “On a constructive proof of Kolmogorov’s superposition theorem”, Constructive Approximation journal, 30 (2009), 653 doi:10.1007/s00365-009-9054-2 | DOI

[2] Cybenko, G. V., “Approximation by Superpositions of a Sigmoidal function”, Mathematics of Control Signals and Systems, 2 (1989), 303–314 | DOI | Zbl

[3] Sprecher, David A., “On the Structure of Continuous Functions of Several Varia”, Trans. Amer. Math. Soc., 1965, 340–355 | DOI | Zbl

[4] Funahashi K., “On the Approximate Realization of Continuous Mappings by Neural Networks”, Neural Networks, 2 (1989), 183–192 | DOI

[5] He K., Zhang X., Ren S., Sun J., “Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification”, arXiv:1502.01852, 2015

[6] Liang S., Srikant R., “Why deep neural networks for function approximation?”, Published as a conference paper at ICLR, 2017

[7] Hanin B., “Universal Function Approximation by Deep Neural Nets with Bounded Width and ReLU Activations”, Mathematics, 7 (2019), 992 | DOI

[8] Liu B., Liang Y., “Optimal function approximation with ReLU neural networks”, Neurocomputing, 435 (2021), 216–227 | DOI

[9] Almira J. M., Lopez-de-Teruel P. E., Romero-López D. J., Voigtlaender F., “Negative results for approximation using single layer and multilayer feedforward neural networks”, Journal of Mathematical Analysis and Applications, 494:1 (2021), 124584 | DOI | Zbl

[10] Guliyev N. J., Ismailov V. E., “On the approximation by single hidden layer feedforward neural networks with fixed weights”, Neural Networks, 98 (2018), 296–304 | DOI | Zbl

[11] Guliyev N. J., Ismailov V. E., “Approximation capability of two hidden layer feedforward neural networks with fixed weights”, Neurocomputing, 316 (2018), 262–269 | DOI

[12] Kolmogorov A. N., “O predstavlenii nepreryvnykh funktsiy mnogikh peremennykh v vide superpozitsii nepreryvnykh funktsiy odnoy peremennoy”, Doklady AN SSSR, 114 (1957), 953-956 (In Russian) | Zbl

[13] Arnold V. I., “O predstavlenii funktsiy neskol'kikh peremennykh v vide superpozitsii funktsiy men'shego chisla peremennykh”, Matematicheskoye prosveshcheniye, 3 (1958), 41–61 (In Russian) | Zbl