报告摘要：In this talk, we first briefly review the mathematical models and their well-posedness for ultrasound tomography. Then, we proposed several machine learning based approaches for efficient solving the corresponding inverse problems. Various numerical examples are provided to demonstrate the efficiency of our new approach.

报告人简介：
Maxim Shishlenin, Dr. Sc. In Computational Mathematics, Professor of the Russian Academy of Sciences, is a specialist in the theory and numerical methods for inverse and ill-posed posed problems of acoustic tomography, seismic, medicine, biology and socio-economic processes.
He is
- Deputy Director for Science of the Sobolev Institute of Mathematics, Novosibirsk,
- Chief Researcher at the Laboratory of Applied Inverse Problems of the Sobolev Institute of Mathematics,
- Head of the Laboratory of Inverse Problems of Natural Science of the Institute of Computational Mathematics and Mathematical Geophysics, Novosibirsk,
- Managing Editor of the Journal of Inverse and Ill-Posed Problems; Deputy Editor-in-Chief of the Journal of Applied and Industrial Mathematics, - Member of the editorial boards of the Numerical Analysis and Applications, Eurasian Journal of Mathematical and Computer Applications, Siberian Electronic Mathematical Reports;
- member of Section "Mathematical modeling on supercomputers of ex- and zettaflops productivity" of the Scientific and Technical Council of the National Center for Physics and Mathematics.