Neural Networks and Classical Algorithms in Inverse Problems of Anomalous Diffusion - Conference attendances

Neural Networks and Classical Algorithms in Inverse Problems of Anomalous Diffusion Conference attendances

Language

Английский

Participant type

Секционный

Conference

Science and Artificial Intelligence Conference, S.A.I.ence
14-15 Nov 2020 , Новосибирск

Authors

Dedok V.A. ¹ , Bugueva T.V. ¹

Affiliations

1	Sobolev Institute of Mathematics

The paper develops a new numerical method for inverse problem solving. This method can be classified as a predictor-corrector method, in which an artificial neural network plays the role of a predictor, and a gradient method plays the role of a corrector. We apply this method to inverse anomalous diffusion problem and show its statistical efficiency. Index Terms—inverse problems, anomalous diffusion, artificial neural networks, numerical methods.

Dedok V.A. , Bugueva T.V.
Neural Networks and Classical Algorithms in Inverse Problems of Anomalous Diffusion
Science and Artificial Intelligence Conference, S.A.I.ence 14-15 Nov 2020