DeepAI AI Chat
Log In Sign Up

Mathematical Foundations for a Compositional Account of the Bayesian Brain

by   Toby St. Clere Smithe, et al.

This dissertation reports some first steps towards a compositional account of active inference and the Bayesian brain. Specifically, we use the tools of contemporary applied category theory to supply functorial semantics for approximate inference. To do so, we define on the `syntactic' side the new notion of Bayesian lens and show that Bayesian updating composes according to the compositional lens pattern. Using Bayesian lenses, and inspired by compositional game theory, we define categories of statistical games and use them to classify various problems of statistical inference. On the `semantic' side, we present a new formalization of general open dynamical systems (particularly: deterministic, stochastic, and random; and discrete- and continuous-time) as certain coalgebras of polynomial functors, which we show collect into monoidal opindexed categories (or, alternatively, into algebras for multicategories of generalized polynomial functors). We use these opindexed categories to define monoidal bicategories of cilia: dynamical systems which control lenses, and which supply the target for our functorial semantics. Accordingly, we construct functors which explain the bidirectional compositional structure of predictive coding neural circuits under the free energy principle, thereby giving a formal mathematical underpinning to the bidirectionality observed in the cortex. Along the way, we explain how to compose rate-coded neural circuits using an algebra for a multicategory of linear circuit diagrams, showing subsequently that this is subsumed by lenses and polynomial functors. Because category theory is unfamiliar to many computational neuroscientists and cognitive scientists, we have made a particular effort to give clear, detailed, and approachable expositions of all the category-theoretic structures and results of which we make use.


Compositional Active Inference II: Polynomial Dynamics. Approximate Inference Doctrines

We develop the compositional theory of active inference by introducing a...

Compositional Active Inference I: Bayesian Lenses. Statistical Games

We introduce the concepts of Bayesian lens, characterizing the bidirecti...

Cyber Kittens, or Some First Steps Towards Categorical Cybernetics

We define a categorical notion of cybernetic system as a dynamical reali...

Polynomial Life: the Structure of Adaptive Systems

We extend our earlier work on the compositional structure of cybernetic ...

Bayesian Updates Compose Optically

Bayes' rule tells us how to invert a causal process in order to update o...

Open dynamical systems as coalgebras for polynomial functors, with application to predictive processing

We present categories of open dynamical systems with general time evolut...

Approximate Inference via Fibrations of Statistical Games

We characterize a number of well known systems of approximate inference ...