IC Colloquium: Mirroring the world: How symmetry shapes hierarchical beliefs
By: Fernando Rosas - University of Sussex
Video of his talk
Abstract
Many systems exhibit nested emergent layers with their own rules and regularities, and our knowledge about them seems naturally organised around these levels. In this talk, I will put forward a formal approach to capture this correspondence, linking hierarchical structures in objective processes to Bayesian beliefs held by observers. For doing this, I will first present a framework to formalise the existence of self-contained levels via the concepts of informational, causal, and computational closure. Then, I will introduce a formal approach to world modelling, examining what it means to build an efficient internal representation of a perception-action loop. Finally, we will put these ideas together to identify equivariance of objective dynamics as a sufficient condition for the existence of multi-level beliefs. These ideas will be illustrated by a range of examples from statistical mechanics and computational neuroscience.
Bio
Fernando Rosas trained in mathematics and engineering at the Pontificia Universidad Católica de Chile (BSc, MSc, PhD), with additional undergraduate study in music composition and philosophy. He held postdoctoral positions at KU Leuven, National Taiwan University, and Imperial College London. He now works as Assistant Professor at the University of Sussex, being also a Research Fellow at Imperial College London and the University of Oxford.
More information
Video of his talk
Abstract
Many systems exhibit nested emergent layers with their own rules and regularities, and our knowledge about them seems naturally organised around these levels. In this talk, I will put forward a formal approach to capture this correspondence, linking hierarchical structures in objective processes to Bayesian beliefs held by observers. For doing this, I will first present a framework to formalise the existence of self-contained levels via the concepts of informational, causal, and computational closure. Then, I will introduce a formal approach to world modelling, examining what it means to build an efficient internal representation of a perception-action loop. Finally, we will put these ideas together to identify equivariance of objective dynamics as a sufficient condition for the existence of multi-level beliefs. These ideas will be illustrated by a range of examples from statistical mechanics and computational neuroscience.
Bio
Fernando Rosas trained in mathematics and engineering at the Pontificia Universidad Católica de Chile (BSc, MSc, PhD), with additional undergraduate study in music composition and philosophy. He held postdoctoral positions at KU Leuven, National Taiwan University, and Imperial College London. He now works as Assistant Professor at the University of Sussex, being also a Research Fellow at Imperial College London and the University of Oxford.
More information
Practical information
- General public
- Free
Contact
- Host: Michael Gastpar