Doktorander inom AI

Information about the research group
The Computer Vision Group conducts research in the field of automatic image interpretation and perceptual scene understanding. The group targets both medical applications, such as the development of new and more effective methods and systems for analysis, support and diagnostics, as well as general computer vision applications including autonomously guided vehicles (particularly self-driving cars), image-based localization, structure-from-motion and object recognition. The main research problems include mathematical theory, algorithms and machine learning (deep learning) for inverse problems in artificial intelligence.

Information about the projects
Topic 1: Learning and Leveraging Rich Priors for Factorization Problems
In this project we are interested in developing methods that combine traditional (parametric) mathematical formulations induced by domain expertise with (non-parametric) models learned from examples. Parametric models inject domain knowledge into learning-based approaches and have therefore the potential to massively reduce the necessary amount of training data. Additionally, the output can be constrained e.g. to be physically plausible, which is difficult to guarantee with pure learning-based architectures. At the same time, being able to incorporate learned priors has the potential to regularize problems where a physical model is not sufficient to guarantee a well posed formulation. From a theoretical point of view we are interested in results that characterize formulations in terms of their expressiveness and generalization as well as developing efficient inference approaches.

Our main application of interest are factorization-based problems, in particular non-rigid structure-from-motion (NRSfM), which aims to infer 3D models of dynamic scenes or objects from videos or multiple images. In contrast to its rigid counterpart, NRSfM is far less mature and it is inherently an ill posed problem requiring suitable priors that disambiguate the effects of camera motion and object deformation. Hence, this project enables research at the intersection of 3D computer vision, factorization methods and machine learning.

Wallenberg AI, Autonomous Systems and Software Program (WASP) is Sweden’s largest individual research program ever, a major national initiative for strategically motivated basic research, education and faculty recruitment. The program addresses research on artificial intelligence and autonomous systems acting in collaboration with humans, adapting to their environment through sensors, information and knowledge, and forming intelligent systems-of-systems.

The vision of WASP is excellent research and competence in artificial intelligence, autonomous systems and software for the benefit of Swedish industry.

The graduate school within WASP is dedicated to provide the skills needed to analyze, develop, and contribute to the interdisciplinary area of artificial intelligence, autonomous systems and software. Through an ambitious program with research visits, partner universities, and visiting lecturers, the graduate school actively supports forming a strong multi-disciplinary and international professional network between PhD-students, researchers and industry.

Read more here.

Topic 2: Energy-based models for supervised deep neural networks and their applications
Despite deep  learning-based  methods  being  the  state-of-the-art  in  many  AI-related  applications,  there  is  a lack  of  consensus  of  how  to  understand  and  interpret  deep  neural  networks  in  order  to  reason  about  their strengths and weaknesses.  Energy-based models in machine learning have a long tradition as a framework to learn from unlabeled data, i.e. unsupervised learning.  Recently, it has been shown that supervised learning of deep neural networks using the back propagation method is a limit case of a suitably defined approach for learning energy-based models using a so-called contrastive loss. This connection motivates our research on further connections between deep learning and energy-based models. In particular, the design of energy-based models, suitable learning losses and corresponding optimization methods are topics addressed in this project. We also aim to explore the benefits of energy-based models for deep neural networks in the following aspects: prediction uncertainty and input confidence, learning efficiency, formal robustness and explainability.

Funding for this position has been obtained from the Chalmers AI Research Centre (CHAIR). CHAIR is a relatively new research centre aiming to increase Chalmers’ expertise and excellence in artificial intelligence. For more information about CHAIR please visit click here.

Major responsibilities
Your major responsibilities are to pursue your own doctoral studies. You are expected to develop your own scientific concepts and communicate the results of your research verbally and in writing, both in Swedish and in English. The position generally also includes teaching on Chalmers' undergraduate level or performing other duties corresponding to 20 per cent of working hours.

Position summary
Full-time temporary employment. The position is limited to a maximum of five years.

Qualifications
To qualify as a PhD student, you must have a master's level degree corresponding to at least 240 higher education credits in a relevant field (physics, mathematics or computer science). The position requires sound verbal and written communication skills in Swedish and English. If Swedish is not your native language, you should be able to teach in Swedish after two years. Chalmers offers Swedish courses

Chalmers continuously strives to be an attractive employer. Equality and diversity are substantial foundations in all activities at Chalmers.

Application procedure
Link to the application can be found here

Application deadline: 15th July - 2020

For questions, please contact:
Christopher Zach, Professor, Electrical Engineering
zach@chalmers.se