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.
Presented by the member of Editorial Board:A. G. Kushner