Geodesic
Model of approximation of multidimensional
News of the Kabardin-Balkar scientific center of RAS, no. 6-3 (2018), pp. 34-40.

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

The article presents a model of approximation of multidimensional functions based on the apparatus of multiagent existential mappings (MEM). The applicability theorems of MEM in problems of approximation of functions of several variables are formulated and proved. The developed model is a constructive combination of the functionality of bioinspired methods and has the following advantages: universality, autonomy of the approximation process, as well as the ability to control the accuracy and time of the learning process
Keywords: artificial intelligence, decision making, cognitive architectures, multi-agent systems, approximation of multidimensional functions, pattern recognition. 
@article{IZKAB_2018_6-3_a2,
     author = {Z. V. Nagoev and I. A. Pshenokova},
     title = {Model of approximation of multidimensional},
     journal = {News of the Kabardin-Balkar scientific center of RAS},
     pages = {34--40},
     publisher = {mathdoc},
     number = {6-3},
     year = {2018},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/IZKAB_2018_6-3_a2/}
}
TY  - JOUR
AU  - Z. V. Nagoev
AU  - I. A. Pshenokova
TI  - Model of approximation of multidimensional
JO  - News of the Kabardin-Balkar scientific center of RAS
PY  - 2018
SP  - 34
EP  - 40
IS  - 6-3
PB  - mathdoc
UR  - http://geodesic.mathdoc.fr/item/IZKAB_2018_6-3_a2/
LA  - ru
ID  - IZKAB_2018_6-3_a2
ER  - 
%0 Journal Article
%A Z. V. Nagoev
%A I. A. Pshenokova
%T Model of approximation of multidimensional
%J News of the Kabardin-Balkar scientific center of RAS
%D 2018
%P 34-40
%N 6-3
%I mathdoc
%U http://geodesic.mathdoc.fr/item/IZKAB_2018_6-3_a2/
%G ru
%F IZKAB_2018_6-3_a2
Z. V. Nagoev; I. A. Pshenokova. Model of approximation of multidimensional. News of the Kabardin-Balkar scientific center of RAS, no. 6-3 (2018), pp. 34-40. http://geodesic.mathdoc.fr/item/IZKAB_2018_6-3_a2/

[1] D. Gilbert, Izbrannye trudy, v 2 t., eds. Pod red. A.N. Parshina, Faktorial, M., 1998

[2] A. N. Kolmogorov, “O predstavlenii nepreryvnykh funktsii neskolkikh peremennykh superpozitsiyami nepreryvnykh funktsii menshego chisla peremennykh”, Doklady AN SSSR, 108 (1956), 179–182 | Zbl

[3] V. I. Arnold, “O predstavlenii funktsii neskolkikh peremennykh v vide superpozitsii funktsii menshego chisla peremennykh”, Matematicheskoe prosveschenie, 1958, no. 3, 41–61 | Zbl

[4] A. Yu. Golubkov, “Postroenie vneshnikh i vnutrennikh funktsii predstavleniya nepreryvnykh funktsii mnogikh peremennykh superpozitsiei nepreryvnykh funktsii odnogo peremennogo”, Fundamentalnaya i prikladnaya matematika, 8:1 (2002), 27–38, MGU | MR | Zbl

[5] V. V. Kruglov, M. I. Dli, R. Yu. Golunov, Nechetkaya logika i iskusstvennye neironnye seti, Fizmatlit, M., 2001, 224 pp.

[6] I. M. Mordashev, “Approksimatsiya funktsii neskolkikh peremennykh summoi menshego chisla peremennykh”, DAN SSSR, 183:4 (1968), 778–779 | MR | Zbl

[7] V. V. Pospelov, O priblizhenii funktsii neskolkikh peremennykh proizvedeniyami funktsii odnogo peremennogo, Institut prikladnoi matematiki AN SSSR, M., 1978, 72 pp. (preprint No32)

[8] V. A. Terekhov, D. V. Efimov, I. Yu. Tyukin, V. N. Antonov, Neirosetevye sistemy upravleniya, Izd-vo SPbGU, SPb., 1999, 265 pp.

[9] M. R. Shura-Bura, “Approksimatsiya funktsii mnogikh peremennykh funktsiyami, kazhdaya iz kotorykh zavisit ot odnogo peremennogo”, Vychislitelnaya matematika, 1957, no. 27, 3–19 | Zbl

[10] I. M. Aleksandrova, V. A. Prourzin, “Metod affinnykh preobrazovanii v zadache ravnomernoi approksimatsii funktsii mnogikh peremennykh”, Voprosy mekhaniki i protsessov upravleniya, Vyp. 18 Matematicheskie voprosy analiza negladkikh modelei, SPbGU, 1995, 19–30

[11] A. V. Timofeev, “Metody obucheniya i samoorganizatsii polinomialnykh neironnykh setei v zadachakh raspoznavaniya obrazov”, Matematicheskie metody raspoznavaniya obrazov, 11:1 (2003), 187–191

[12] S. Khaikin, Neironnye seti. Polnyi kurs, Vilyams, M., 2006

[13] A. I. Galushkin, Neironnye seti. Osnovy teorii, Goryachaya Liniya Telekom, M., 2010

[14] K. Hornik, “Approximation Capabilities of Multilayer Feedforward Networks”, Neural Net-works, 4:2 (1991), 251–257 | DOI | MR

[15] K. Hornik, “Some New Results on Neural Networks Approximation”, Neural Networks, 6:8 (1993), 1069–1072 | DOI

[16] A. R. Barron, “Universal Approximation Bounds for Superpositions of a Sigmoidal Function”, IEEE Trans. Information Theory, 39:3 (1993), 930–945 | DOI | MR | Zbl

[17] V. Kurkova, “Approximation of Functions by Perceptron Networks with Bounded Number of Hidden Units”, Neural Networks, 8:5 (1995), 745–750 | DOI

[18] G. V. Cybenko Approximation by Superpositions of a Sigmoidal function, Mathematics of Control Signals and Systems, 2:4 (1989), 303–314 | DOI | MR | Zbl

[19] F. Rozenblatt, Printsipy neirodinamiki: pertseptrony i teoriya mekhanizmov mozga, Mir, M., 1965

[20] A. N. Gorban, “Obobschennaya approksimatsionnaya teorema i vychislitelnye vozmozhnosti neironnykh setei”, Sibirskii zhurnal vychislitelnoi tekhniki, 1:1 (1998), 12–24 | MR | Zbl

[21] G. V. Cybenko, “Approximation by Superpositions of a Sigmoidal function”, Mathematics of Control Signals and Systems, 2:4 (1989), 303–314 | DOI | MR | Zbl

[22] V. V. Vyugin, Elementy matematicheskoi teorii mashinnogo obucheniya, ucheb. posobie., MFTI: IPPI RAN, M., 2010, 231 pp.

[23] V. N. Vapnik, A. Ya. Chervonenkis, Teoriya raspoznavaniya obrazov (statisticheskie problemy obucheniya), Nauka, M., 1974, 416 pp.

[24] Bellman. R.E., Dynamic Programming (Dover paperback ed.), Princeton University Press, Howard, Princeton, NJ, (2003) [1957] | MR

[25] A. Ronald, Dynamic Programming and Markov Processes, The M.I.T. Press, 1960 | MR | Zbl

[26] S. Rassel, P. Norvig, Iskusstvennyi intellekt: sovremennyi podkhod, 2-e izd, Izdatelskii dom «Vilyame», M., 2006 (per. s angl)

[27] T. Hastie, R. Tibshirani, J. Friedman, The Elements of Statistical Learning, Springer, 2014, 739 pp. | MR

[28] Z. V. Nagoev, Intellektika ili Myshlenie v zhivykh i iskusstvennykh sistemakh, Izdatelstvo KBNTs RAN, Nalchik, 2013, 211 pp.

[29] K. Vorontsov, Mashinnoe obuchenie. Kurs lektsii http://www.machinelearning.ru

[30] Sutton Richard S., Barto, G. Andrew, Reinforcement Learning: An Introduction, MIT Press, 1998 | MR

[31] P. Kaelbling Leslie, L. Littman Michael, W. Moore Andrew, “Reinforcement Learning: A Survey”, Journal of Artificial Intelligence Research, 19964, 237–285 | MR

[32] N. Viner, Kibernetika ili Upravlenie i svyaz v zhivotnom i mashine, Sovetskoe radio, M., 1958

[33] V. M. Kureichik, A. A. Kazharov, “Ispolzovanie roevogo intellekta v reshenii NP-trudnykh zadach”, Izvestiya YuFU. Tekhnicheskie nauki, 2011, no. 7 (120), 30–37

[34] A. Orlov, A. Glushchenko, V. Kureichik, “Hybrid genetic algorithm for cutting stock and packaging problems”, EWDTS 2016, art, art. no. 7807680

[35] J. J. Hopfield, D. W. Tank, “«Neural» computation of decisions in optimization problems”, Biological Cybernetics, 52:3 (1985), 141–152 | MR | Zbl

[36] Salakhutdinov Ruslan, Learning deep generative models. proquest.com (PhD thesis), University of Toronto, 2009

[37] Z. V. Nagoev, “Multiagentnye ekzistentsialnye otobrazheniya i funktsii”, Izvestiya Kabardino-Balkarskogo nauchnogo tsentra RAN, 2013, no. 4 (54), 63–71