Inverse problems of anomalous diffusion theory: An artificial neural network approach
- Authors: Bondarenko A.N.1, Bugueva T.V.1,2, Dedok V.A.1
-
Affiliations:
- Sobolev Institute of Mathematics
- Novosibirsk State University
- Issue: Vol 10, No 3 (2016)
- Pages: 311-321
- Section: Article
- URL: https://journals.rcsi.science/1990-4789/article/view/212392
- DOI: https://doi.org/10.1134/S1990478916030017
- ID: 212392
Cite item
Abstract
The results are presented of computer simulation of the operation of a three-layer perceptron trained for solving inverse problems of anomalous diffusion theory. Several types of inverse problems are considered, including the problem of determining the Hurst exponent of a selfsimilar medium.
About the authors
A. N. Bondarenko
Sobolev Institute of Mathematics
Author for correspondence.
Email: bondarenkoan1953@mail.ru
Russian Federation, pr. Akad. Koptyuga 4, Novosibirsk, 630090
T. V. Bugueva
Sobolev Institute of Mathematics; Novosibirsk State University
Email: bondarenkoan1953@mail.ru
Russian Federation, pr. Akad. Koptyuga 4, Novosibirsk, 630090; ul. Pirogova 2, Novosibirsk, 630090
V. A. Dedok
Sobolev Institute of Mathematics
Email: bondarenkoan1953@mail.ru
Russian Federation, pr. Akad. Koptyuga 4, Novosibirsk, 630090