Postdoctoral position in deep learning based sparse view tomography - Hiring in process/Finished, not possible to apply

At the Division of Systems and Control, we develop both theory and concrete tools for learning, reasoning, and acting based on data. An overarching goal is for both humans and machines to better understand the complexity of the real world. Probabilistic models form a central part of our research, allowing us to systematically represent and cope with the uncertainty inherent in most data.  Data and learning algorithms are also important components of our research. It remains a major challenge to develop efficient and accurate learning algorithms capable of handling high-dimensional models, data rich applications, complex model structures, and diverse data sources that arise in many of the data analysis problems that we are currently facing.

We have a wide network of strong international collaborators all around the world, for example at the University of Cambridge, University of Oxford, University of British Columbia, University of Sydney, University of Newcastle and Aalto University. There are also ample opportunities for collaborations with other leading machine learning groups in Sweden and Europe, through our affiliations with WASP (https://wasp-sweden.org/) and the ELLIS society (https://ellis.eu/), respectively.

Read more about our benefits and what it is like to work at Uppsala University

Duties
We offer a two-year postdoctoral fellowship based on a grant from Kjell and Märta Beijer Foundation and the Tandem Forest Values programme at the Royal Swedish Academy of Agriculture and Forestry.

The position includes research into theory and development of deep learning algorithms for computer vision regression tasks in tomographic image reconstruction, meaning that input is noisy sparse view tomographic data of an object. One aim is to extend energy-based models for deep probabilistic regression to such a setting, e.g., by including a handcrafted physics model for generating data from an image. Work will be spearheaded by the need to detect and locate interior imperfections (cracks, knots, metallic inserts, etc.) of logs from sparse view tomographic data. This application is part of a collaboration with a larger international project supported by the Academy of Finland involving researchers at LUT-University and University of Oulu with an overall goal of developing methods for image guided optimization of the sawline in processing of forest logs. It is also part of a recently initiated collaboration with researchers at the Wood Science and Engineering at Luleå University of Technology.

The research will be pursued at the Department of Information Technology at Uppsala University. As a postdoctoral fellow, you will benefit from the strong research environments at Uppsala University in machine learning.

Requirements
PhD degree in mathematics, signal processing, computer science, or computational physics/engineering or a foreign degree equivalent to a PhD degree in mathematics, signal processing, computer science, or computational physics/engineering. The degree needs to be obtained by the time of the decision of employment. Those who have obtained a PhD degree three years prior to the application deadline are primarily considered for the employment. The starting point of the three-year frame period is the application deadline. Due to special circumstances, the degree may have been obtained earlier. The three-year period can be extended due to circumstances such as sick leave, parental leave, duties in labour unions, etc.

The candidate must have a strong background from machine learning or signal/image processing with experience from software development in scientific computing or machine learning using Python and/or C/C++. Finally, a successful candidate must be strongly motivated and have the capability to work independently as well as in collaboration with members of the research group.

Additional qualifications
Experience from tomographic image reconstruction is highly desirable. An additional advantage is a research track record with publications at leading conferences in machine learning. As a person, you are creative, thorough and have a structured approach. When selecting among the applicants we will assess their ability to independently drive their work forward, to collaborate with others, to have a professional approach and to analyze and work with complex problems. Great emphasis will be placed on personal characteristics and personal suitability.

About the employment
The employment is a temporary position of 2 years according to central collective agreement. Scope of employment 100 %. Starting date upon agreement, but preferably no later than 31 March 2022 or as agreed. Placement: Uppsala.

Application: The application must contain:

1. A curriculum vitae (CV),
2. A copy of relevant grade documents (translated into Swedish or English),
3. A list of publications
4. Up to five selected publications in electronic format
5. A research statement describing your past and current research (max 1 page) and a proposal for future activities (max 1 page).
6. Contact information for two references.
7. A cover letter briefly describing your motivation for applying for this position and the earliest possible employment date (max 1 page).

For further information about the position, please contact: Professor Ozan Öktem (phone: +46-733-52 2185, e-mail: ozan.oktem@it.uu.se) or Professor Thomas Schön (phone: +46-18-471 2594, e-mail: thomas.schon@it.uu.se).

Please submit your application by 4th February 2022, UFV-PA 2021/5142.

Are you considering moving to Sweden to work at Uppsala University? Find out more about what it´s like to work and live in Sweden.