DeepAI AI Chat
Log In Sign Up

Cyber Kittens, or Some First Steps Towards Categorical Cybernetics

by   Toby St. Clere Smithe, et al.

We define a categorical notion of cybernetic system as a dynamical realisation of a generalized open game, along with a coherence condition. We show that this notion captures a wide class of cybernetic systems in computational neuroscience and statistical machine learning, exposes their compositional structure, and gives an abstract justification for the bidirectional structure empirically observed in cortical circuits. Our construction is built on the observation that Bayesian updates compose optically, a fact which we prove along the way, via a fibred category of state-dependent stochastic channels.


page 1

page 2

page 3

page 4


Mathematical Foundations for a Compositional Account of the Bayesian Brain

This dissertation reports some first steps towards a compositional accou...

A Corpus-based Toy Model for DisCoCat

The categorical compositional distributional (DisCoCat) model of meaning...

Bayesian Updates Compose Optically

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

Composable constraints

We introduce a notion of compatibility between constraint encoding and c...

Dependent Bayesian Lenses: Categories of Bidirectional Markov Kernels with Canonical Bayesian Inversion

We generalise an existing construction of Bayesian Lenses to admit lense...

Relating Apartness and Bisimulation

A bisimulation for a coalgebra of a functor on the category of sets can ...

Space-time tradeoffs of lenses and optics via higher category theory

Optics and lenses are abstract categorical gadgets that model systems wi...