The Natural Language Processing Group at Linköping University and the Foundations of Language Processing Group at Umeå University are looking for candidates for two (2) positions as PhD Students in Computer Science.
The positions are announced in the project “A Practical Theory of Computation for Modern Neural Network Architectures”. The project is funded by the Wallenberg AI, Autonomous Systems and Software Program (WASP), a major national initiative for strategically motivated basic research, education and faculty recruitment. It is by far the largest individual research programme in Sweden.
You will work closely together with and be supervised by project leaders Marco Kuhlmann at the Department of Computer and Information Science, Linköping University, and Frank Drewes at the Department of Computing Science, Umeå University.
Each of the positions runs for four years without teaching duties, or five years with teaching duties constituting 20% of the overall workload.
More about the positions
Neural networks are today the most important computational paradigm for AI and machine learning. While their computational power has been studied for decades, the theoretical development has not been able to keep up with the recent upshot of new neural architectures, such as the Transformer. Also, existing theoretical results are of limited practical value because they often apply to monolithic architectures, whereas applications typically use networks that are composed of re-usable components. Moreover, theoretical results tend to make idealising assumptions such as infinite precision or unlimited training time, rather than acknowledging that such commodities are in short supply and should thus be treated as parameters of expressive power. In this project, we want to address these shortcomings and develop a practical theory of computation for modern neural network architectures.
The project combines methods from theoretical computer science – especially the theory of computation and formal languages – with empirical validation in natural language processing (NLP). We therefore welcome candidates from both areas.
Master’s degree in computer science or other relevant field
Relevant courses and excellent grades in project-related subjects
Ability to work both independently and in a team
Creativity and the willingness to actively pursue your own development as a researcher
Fluency in written and spoken English