|
Avtomatika i Telemekhanika, 2018, Issue 9, Pages 95–105
(Mi at15205)
|
|
|
|
This article is cited in 14 scientific papers (total in 14 papers)
Intellectual Control Systems, Data Analysis
Learning radial basis function networks with the trust region method for boundary problems
L. N. Elisova, V. I. Gorbachenkob, M. V. Zhukovb a Moscow State Technical University of Civil Aviation, Moscow, Russia
b Penza State University, Penza, Russia
Abstract:
We consider the solution of boundary value problems of mathematical physics with neural networks of a special form, namely radial basis function networks. This approach does not require one to construct a difference grid and allows to obtain an approximate analytic solution at an arbitrary point of the solution domain. We analyze learning algorithms for such networks. We propose an algorithm for learning neural networks based on the method of trust region. The algorithm allows to significantly reduce the learning time of the network.
Keywords:
boundary value problems of mathematical physics, radial basis function networks, learning of neural networks, method of trust region.
Citation:
L. N. Elisov, V. I. Gorbachenko, M. V. Zhukov, “Learning radial basis function networks with the trust region method for boundary problems”, Avtomat. i Telemekh., 2018, no. 9, 95–105; Autom. Remote Control, 79:9 (2018), 1621–1629
Linking options:
https://www.mathnet.ru/eng/at15205 https://www.mathnet.ru/eng/at/y2018/i9/p95
|
Statistics & downloads: |
Abstract page: | 186 | Full-text PDF : | 72 | References: | 24 | First page: | 12 |
|