|
This article is cited in 29 scientific papers (total in 29 papers)
Solving boundary value problems of mathematical physics using radial basis function networks
V. I. Gorbachenko, M. V. Zhukov Penza State University, Penza, Russia
Abstract:
A neural network method for solving boundary value problems of mathematical physics is developed. In particular, based on the trust region method, a method for learning radial basis function networks is proposed that significantly reduces the time needed for tuning their parameters. A method for solving coefficient inverse problems that does not require the construction and solution of adjoint problems is proposed.
Key words:
boundary value problems of mathematical physics, neural networks, radial basis function networks, learning of neural networks, trust region method, coefficient inverse problems.
Received: 03.02.2016 Revised: 27.06.2016
Citation:
V. I. Gorbachenko, M. V. Zhukov, “Solving boundary value problems of mathematical physics using radial basis function networks”, Zh. Vychisl. Mat. Mat. Fiz., 57:1 (2017), 133–143; Comput. Math. Math. Phys., 57:1 (2017), 145–155
Linking options:
https://www.mathnet.ru/eng/zvmmf10513 https://www.mathnet.ru/eng/zvmmf/v57/i1/p133
|
Statistics & downloads: |
Abstract page: | 501 | Full-text PDF : | 164 | References: | 44 | First page: | 33 |
|