Bayesian inversion for tomography through machine learning

Ozan Oktem
KTH

Wednesday 19 June 2019
14:15 - 15:15
Room EM 1.83

Abstract

The talk will outline recent approaches for using (deep) convolutional neural networks to solve a wide range of inverse problems, such as tomographic image reconstruction. Emphasis is on learned iterative schemes that use a neural network architecture for reconstruction which includes physics-based models for how data is generated. The talk will also discuss recent developments in using generative adversarial networks for uncertainty quantification in inverse problems.

This is a joint AMS, Maths and CS seminar.

Host: Marcelo Pereyra