Postdoc position in the Data Science and AI division at the Department of Computer Science and Engineering, Chalmers University of Technology.
Information about the project
The position is placed in the research group led by Fredrik Johansson, currently comprised of 5 PhD students working on topics related to machine learning for improved decision making with applications in healthcare.
Supervised machine learning (ML) has become an essential tool for scientists and engineers. This is no doubt in part due to the simplicity of its default implementation: 1) Pick a measure of error as learning objective; 2) Collect a data set of sample inputs and outputs; 3) Fit a model which returns outputs with minimal average error on inputs from the data set. This approach, empirical risk minimization, has proved tremendously successful in diverse domains but is sensitive to changes in input domain, to interventions on key variables or to small sample sizes. This position will explore machine learning methods and theory which go beyond this idea to provide stronger guarantees and more efficient learning through, for example, causal analysis or theory on domain generalization. These are examples; you will have large influence to define your project.
The candidate is expected to pursue research into machine learning in the context of (causal) interventions, changes in input domains or tasks, or small-sample learning (see description above). Other directions can be explored if there is mutual interest with the advisor and/or PhD students in the group. Ideas inspired by applications in healthcare are encouraged, but profiles with a strong methodological or theoretical record are preferred. The candidate will have large influence in the specific projects pursued during the postdoc.