Cyber Kittens, or Some First Steps Towards Categorical Cybernetics
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Jan 2021.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 1; 2022: 1; 2023: 1; 2024: 1.
4 papers.
- 2024Towards Compositional Interpretability for XAIcited by 10
- 2021Interpreting Dynamical Systems as Bayesian Reasonerscited by 5
- 2023Active Inference in String Diagrams: A Categorical Account of Predictive Processing and Free Energycited by 3
- 2022Compositional Active Inference II: Polynomial Dynamics. Approximate Inference Doctrinescited by 2
- 2024Towards Compositional Interpretability for XAI25 Jun 2024
- 2023Active Inference in String Diagrams: A Categorical Account of Predictive Processing and Free Energy1 Aug 2023
- 2022Compositional Active Inference II: Polynomial Dynamics. Approximate Inference Doctrines25 Aug 2022
- 2021Interpreting Dynamical Systems as Bayesian Reasoners27 Dec 2021