Solving boundary value problems of mathematical physics using radial basis function networks
Žurnal vyčislitelʹnoj matematiki i matematičeskoj fiziki, Tome 57 (2017) no. 1, pp. 133-143
Voir la notice de l'article provenant de la source Math-Net.Ru
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.
@article{ZVMMF_2017_57_1_a11,
author = {V. I. Gorbachenko and M. V. Zhukov},
title = {Solving boundary value problems of mathematical physics using radial basis function networks},
journal = {\v{Z}urnal vy\v{c}islitelʹnoj matematiki i matemati\v{c}eskoj fiziki},
pages = {133--143},
publisher = {mathdoc},
volume = {57},
number = {1},
year = {2017},
language = {ru},
url = {http://geodesic.mathdoc.fr/item/ZVMMF_2017_57_1_a11/}
}
TY - JOUR AU - V. I. Gorbachenko AU - M. V. Zhukov TI - Solving boundary value problems of mathematical physics using radial basis function networks JO - Žurnal vyčislitelʹnoj matematiki i matematičeskoj fiziki PY - 2017 SP - 133 EP - 143 VL - 57 IS - 1 PB - mathdoc UR - http://geodesic.mathdoc.fr/item/ZVMMF_2017_57_1_a11/ LA - ru ID - ZVMMF_2017_57_1_a11 ER -
%0 Journal Article %A V. I. Gorbachenko %A M. V. Zhukov %T Solving boundary value problems of mathematical physics using radial basis function networks %J Žurnal vyčislitelʹnoj matematiki i matematičeskoj fiziki %D 2017 %P 133-143 %V 57 %N 1 %I mathdoc %U http://geodesic.mathdoc.fr/item/ZVMMF_2017_57_1_a11/ %G ru %F ZVMMF_2017_57_1_a11
V. I. Gorbachenko; M. V. Zhukov. Solving boundary value problems of mathematical physics using radial basis function networks. Žurnal vyčislitelʹnoj matematiki i matematičeskoj fiziki, Tome 57 (2017) no. 1, pp. 133-143. http://geodesic.mathdoc.fr/item/ZVMMF_2017_57_1_a11/