Criteria for minimal RBF artificial neural network’s center vectors set definition

M.A. Abrosimov; A.V. Brovko

Criteria for minimal RBF artificial neural network’s center vectors set definition

research article UDC 004.931, 621.372 Pages: 50-54

¹ Post-graduate Student, Department of Applied Information Technologies, Yuri Gagarin State Technical University of Saratov (SSTU)
² Dr.Sc. (Phys.-Math.), Professor, Department of Applied Information Technologies, Yuri Gagarin State Technical University of Saratov (SSTU)

Keywords: artificial neural network training algorithm for artificial neural network kronecker-capelli theorem rbf ann center vectors

Abstract

This paper points out the problem of defining the center vectors set of RNF artificial neural network. The criteria for sufficient center vectors count is presented. The results of numerical modeling, presented in the paper, confirm a significant reduction of RBF ANN training time with no information loss in hidden layer

How to cite

Абросимов М.А., Бровко А.В. Критерий определения минимального набора базисов для искусственной нейронной сети с радиальными базисными функциями // Нейрокомпьютеры: разработка, применение. 2018. № 3. С. 50–54.

References

Brovko A.V., Murphy E.K., and Yakovlev V.V. Waveguide microwave imaging: neural network reconstruction of functional 2-D permittivity profiles // IEEE Transactions on Microwave Theory and Techniques. 2009. V. 57. № 2. R. 406–414.
Brovko A.V. Metod opredelenija trehmernogo profilja dijelektricheskoj pronicaemosti obrazca s ispol'zovaniem nejrosetevoj matemati-cheskoj modeli // Radiotehnika. 2015. № 10. S. 115–120.
Aksenov S.V., Novosel'cev V.B. Organizacija i ispol'zovanie nejronnyh setej. Tomsk: Tomskij politehnicheskij universitet. 2006.
Hajkin C. Nejronnye seti: polnyj kurs. Izd. 2-e. M.: Vil'jams. 2006.
Fausett L.V. Fundamentals of Neural Networks: Architectures Algorithms and Applications. New Jersey: Prentice-Hall. 1994.
Dolinina O.N., Kuz'min A.K. Metod postroenija testov dlja otladki nejrosetej na osnove tehnicheskoj diagnostiki // Sb. tr. HHIII Mezhdu-nar. nauch. konf. «Matematicheskie metody v tehnike i tehnologijah» (MMTT-23). V 12 t. T. 6. Sekcii 6, 7 / Pod obshh. red. V.S. Balakireva. Saratov: Sarat. gos. tehn. un-t. 2010. S. 38–41.
Ivzhenko S.P. Intellektual'nyj analiz dannyh na osnove kart Kohonena // Tr. XXI Vseros. nauch.-metod. konf. «Telematika'2014» (g. SanktPeterburg, 23–26 ijunja 2014 g.). SPb. 2014. 250 s.

Full text, PDF 350 ₽

[1] Brovko A.V., Murphy E.K., and Yakovlev V.V. Waveguide microwave imaging: neural network reconstruction of functional 2-D permittivity profiles // IEEE Transactions on Microwave Theory and Techniques. 2009. V. 57. № 2. R. 406–414.

[2] Brovko A.V. Metod opredelenija trehmernogo profilja dijelektricheskoj pronicaemosti obrazca s ispol'zovaniem nejrosetevoj matemati-cheskoj modeli // Radiotehnika. 2015. № 10. S. 115–120.

[3] Aksenov S.V., Novosel'cev V.B. Organizacija i ispol'zovanie nejronnyh setej. Tomsk: Tomskij politehnicheskij universitet. 2006.

[4] Hajkin C. Nejronnye seti: polnyj kurs. Izd. 2-e. M.: Vil'jams. 2006.

[5] Fausett L.V. Fundamentals of Neural Networks: Architectures Algorithms and Applications. New Jersey: Prentice-Hall. 1994.

[6] Dolinina O.N., Kuz'min A.K. Metod postroenija testov dlja otladki nejrosetej na osnove tehnicheskoj diagnostiki // Sb. tr. HHIII Mezhdu-nar. nauch. konf. «Matematicheskie metody v tehnike i tehnologijah» (MMTT-23). V 12 t. T. 6. Sekcii 6, 7 / Pod obshh. red. V.S. Balakireva. Saratov: Sarat. gos. tehn. un-t. 2010. S. 38–41.

[7] Ivzhenko S.P. Intellektual'nyj analiz dannyh na osnove kart Kohonena // Tr. XXI Vseros. nauch.-metod. konf. «Telematika'2014» (g. SanktPeterburg, 23–26 ijunja 2014 g.). SPb. 2014. 250 s.

Abstract

How to cite

Related articles