Zur Startseite von DrArbeit.de,
der deutschlandweiten Stellenbörse für Diplomarbeiten und Doktorarbeiten


Archiv - Stellenangebot


Dies ist ein Angebot aus der Datenbank von DrArbeit.de

Um die Datenbank komfortabel nach weiteren Angeboten durchsuchen zu können, klicken Sie einfach oben oder hier.

Archiv-Übersicht     Angebot Nr. 13821

Angebotsdatum: 4. März 2020
Art der Stelle: Doktorarbeit / Diplomarbeit
Fachgebiet: Mathematik > Angewandte Mathematik
Titel des Themas: Deep Learning in Inverse Problems

Institut: Applied Mathematics Group (https://applied-math.uibk.ac.at)
Frau Irene Milewski
Technikerstraße 25
6020 Innsbruck
Tel.:    Fax.:
Homepage: http://(https://docc.eu)
E-Mail Kontakt: mail

Beschreibung: PhD fellowship for a period of three years a in the frame of DP DOCC (https://docc.eu) in the research area of
Deep Learning in Inverse Problems
Proposed project:
Dynamic tomography of complex continua: Deep learning and regularization (NNA-1)
Solving dynamic inverse problems allows real-time imaging of many physiological processes, ranging from cardiovascular imaging to non-invasive surgery monitoring. Standard recovery methods accounting for rapid movements are only suitable for simple rigid motion

NETT deep learning for time dependent inverse problems with unknown forward operator (NNA-2)
Inverse problems arise in various applications ranging from medical imaging to non-destructive testing and remote sensing. Their characteristic feature is the inherent ill-posedness, requiring special techniques for its solution. We recently proposed network Tikhonov regularization (NETT) for inverse problems, which is based on generalized Tikhonov regularization using a neural network as learned regularizer.
Project proposed by the candidate: Please contact the future supervisor, Prof. Markus Haltmeier (markus.haltmeier@uibk.ac.at), for a letter of support if you wish to propose an own project.
Methoden: (NNA-1):We develop and analyse efficient image reconstruction for complex motions, using tools from regularization theory, inverse problems, deep learning and neural networks to integrate suitable a-priori information.
(NNA-2):The aim of this project is to extend the NETT to inverse problems with partial unknown forward operators. In particular, appropriate networks and training strategies will be designed, a convergence analysis developed and an efficient numerical implementation established

Anfangsdatum: 1. Juni 2020
Geschätzte Dauer: 3 Jahre
Bezahlung: annual gross salary of around 40'103 EUR (sus
Sonstiges: DOCC is an interdisciplinary Marie Skłodowska-Curie COFUND doctoral programme at the University of Innsbruck that will train 15 PhD students for 3 years on modelling and simulation of complex dynamical continuum systems. DOCC prepares Europe's next top modellers to link simulations and the real world within a multi-disciplinary environment, by providing beyond essential technical expertise also the training in key abilities to communicate and transfer methods and results.