Our young investigator group leader has been awarded this competitive postdoc grant to continue his work in Bayesian deep learning
is located at Helmholtz Munich, where his research focuses on the interface between Bayesian inference and deep learning. Bayesian statistics help integrate prior knowledge into the deep learning process. Usually artificial intelligence learns blindly from a huge amount of samples, but in many scientific applications those big datasets are not available. However, for many of these subjects there is a lot of theoretical knowledge available. This information could be integrated in the AI before training, allowing a better interpretation of the available data even if it's scarce. Bayesian statistics can help identify how to optimally use prior knowledge in any learning problem, so that AI models can be trained efficiently using way less data.
The goal of Vincent’s group is to use Bayesian inference in deep learning to improve robustness, data-efficiency, and uncertainty estimation in these modern machine learning approaches. Some areas where Bayesian machine learning could be used include intensive care medicine, single-cell multi-omics, and drug design.
Now as a Branco Weiss Fellow, Vincent will continue his work in Bayesian deep learning, aiming to unlock new applications for areas with small datasets available. This competitive grant searches for excellence, and has created a community of exceptional junior researchers from a large spectrum of fields and countries. From Helmholtz AI, we wish the best to our colleague in this new step in his career!