Learning Radial Basis Function Networks with the Trust Region Method for Boundary Problems


Cite item

Full Text

Open Access Open Access
Restricted Access Access granted
Restricted Access Subscription Access

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.

About the authors

L. N. Elisov

Moscow State Technical University of Civil Aviation

Author for correspondence.
Email: lev.el@list.ru
Russian Federation, Moscow

V. I. Gorbachenko

Penza State University

Email: lev.el@list.ru
Russian Federation, Penza

M. V. Zhukov

Penza State University

Email: lev.el@list.ru
Russian Federation, Penza

Supplementary files

Supplementary Files
Action
1. JATS XML

Copyright (c) 2018 Pleiades Publishing, Ltd.