Abstract

Bayesian statistics allows us to quantify the strength of inductive inference from facts (such as experimental data) to propositions such as scientific hypotheses and models. For example, it can be used in searches for physics beyond the standard model and multi-message astronomy to analyze gravitational-wave signals. In our theoretical-physics research, we develop novel machine-learning methods to make the Bayesian approach tractable for heavy computing models.

A general message of this presentation will be that machine-learning practitioners can embrace the Bayesian philosophy to introduce uncertainties and avoid overfitting.

Christian Forssén

Professor in Theoretical Physics @ Chalmers

Christian Forssén is Professor in theoretical physics at Chalmers. He uses high-performance computing, Bayesian statistics, and machine learning to address basic-science questions within theoretical nuclear and particle physics. Christian has supervised research projects for more than 100 bachelor and master students and has been teaching both undergraduate and graduate-level physics classes and advanced courses on Bayesian data analysis and the use of machine learning methods in physics.