Special seminar with Jordi Grau-Moya at the GRASP lab of UPenn. Decision-Making with Information Constraints: Free Energy Foundations and Applications
I am 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. Our group is working on connecting sensorimotor learning with theoretical models for bounded rational decision-making. My research is focused on understanding how decision-makers can leverage the structure of their environment in order to efficiently cope with uncertainty. I investigate links between bounded rationality (lately termed computational rationality) and information theory, in particular rate distortion theory. Building upon these links, I am working on a theoretical framework for information-optimal hierarchical models for inference and decision-making.
Talk at ICRA 2016 workshop on task-driven perceptual representations: sensing, planning and control under resource constraints - Information-theoretic bounde...
Information-theoretic framework for bounded rationality applied to feedforward neural networks, by Felix Leibfried.
Paper published: Bio-inspired feedback-circuit implementation of discrete, free energy optimizing, winner-take-all computations
Genewein T, Braun DA (2016). Bio-inspired feedback-circuit implementation of discrete, free energy optimizing, winner-take-all computations.
Talk at the Cognitive Systems and Machine Learning group, Bosch research Renningen - Hierarchical decision-making in perception-action systems.