Pierre Baudot - Information cohomology and probabilistic topos for consciousness modeling: from elementary perception to machine learning
Pierre Baudot
Median Technologies, Marseille, France.
Elementary quantitative and qualitative aspects of consciousness are investigated conjointly from the biology, neuroscience, physic and mathematic point of view, by the mean of a theory written with Bennequin that derives and extends information theory within algebraic topology. Information structures, that accounts for statistical dependencies within n-body interacting systems are interpreted a la Leibniz within a monadic-panpsychic framework where consciousness is information and physical, and arise from collective interactions. The electrodynamic intrinsic nature of consciousness, sustained by an analogical code, is illustrated by standard neuroscience and psychophysic results. It accounts for the diversity of the learning mechanisms, including adaptive and homeostatic processes on multiple scales, and details their expression within information theory. The axiomatization and logic of cognition are rooted in measure theory expressed within a topos intrinsic probabilistic constructive logic, allowing to express the information of mathematical formula as a Gödel code. Information topology provides a synthesis of the main models of consciousness (integrated information, global neuronal workspace, free energy principle) within a formal Gestalt theory, an expression of information structures and patterns in correspondence with Galois cohomology and symmetries. We give several examples of the application of information topology to standard recognition challenges in AI- machine learning.
Filmed at the Models of Consciousness conference, University of Oxford, September 2019.