Tim Genewein photo

Tim Genewein


Information-optimal hierarchies for inference and decision-making

Bosch Center for Artificial Intelligence
Stuttgart - Renningen, Germany

Email Scholar Github Contact Subscribe

Welcome

I am a researcher in the Deep Learning group at the Bosch Center for Artificial Intelligence working on network compression and Bayesian deep learning. Prior to that, I was a PhD student at the Sensorimotor Learning and Decision-Making research group lead by Daniel A. Braun at the Max Planck Institute for Intelligent Systems and the Max Planck Institute for Biological Cybernetics. My PhD research has been focused on understanding how decision-makers can leverage the structure of their environment in order to efficiently cope with uncertainty. I investigated links between bounded rationality (lately termed computational rationality) and information theory, in particular rate distortion theory. Building upon these links, I am contributing toward a theoretical framework for information-optimal hierarchical models for inference and decision-making. Additionally, I am working on efficient and scalable implementations of these hierarchical models by making use of recent breakthroughs in machine learning, particularly deep learning.

Download CV Download thesis

Latest blog posts

Talk by Jordi Grau-Moya @ ECML 2016

Talk by Jordi Grau-Moya on our paper: Planning with Information-Processing Constraints and Model Uncertainty in Markov Decision Processes

Talk @ GRASP lab, UPenn and UAI 2016

Special seminar with Jordi Grau-Moya at the GRASP lab of UPenn. Decision-Making with Information Constraints: Free Energy Foundations and Applications