Sort by
Refine Your Search
-
processes related to carbon cycling in the soil-plant system Experience with Bayesian inference and machine learning is an asset Ability to work independently and cooperatively as part of an interdisciplinary
-
phenomena such as the spread of misinformation or the formation of filter bubbles. For this, we rely on rigorous probabilistic methods to model and analyse the intrinsic complexities of these systems
-
phenomena such as the spread of misinformation or the formation of filter bubbles. For this, we rely on rigorous probabilistic methods to model and analyse the intrinsic complexities of these systems
-
analyses, an area in which our group has a track record of success (see recent publications below). The TARGET-AI project seeks to apply leading-edge techniques from deep learning and Bayesian modeling
-
opinion dynamics. Our goal is to gain a deeper understanding of phenomena such as the spread of misinformation or the formation of filter bubbles. For this, we rely on rigorous probabilistic methods
-
challenging, and new theoretical methods and algorithms are required. The research project aims at deriving priors for Bayesian methods from atomistic simulations and machine learning. It also offers
-
. Bonus lectures can be picked by the students depending on their interests and project-specific requirements. Students can deepen their knowledge about selected topics (e.g. Bayesian Statistics, HMMs, AI
-
, adversarial attacks, and Bayesian neural networks. Excellent analytical, technical, and problem-solving skills Excellent programming skills in Python and PyTorch including fundamental software engineering