Learning radial basis function networks with the trust region method for boundary problems
Autor: | Vladimir Gorbachenko, L. N. Elisov, Maxim V. Zhukov |
---|---|
Rok vydání: | 2018 |
Předmět: |
Trust region
Mathematical optimization Artificial neural network Computer science Boundary (topology) 010103 numerical & computational mathematics 02 engineering and technology Grid 01 natural sciences Domain (mathematical analysis) Control and Systems Engineering 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Radial basis function Point (geometry) Boundary value problem 0101 mathematics |
Zdroj: | Автоматика и телемеханика. :95-105 |
ISSN: | 0005-2310 |
Popis: | 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. |
Databáze: | OpenAIRE |
Externí odkaz: |