ActInf MathStream 013.1 ~ Alexis Toumi: "DisCoPy: Monoidal Categories for Active Inference"

Alexis Toumi: "DisCoPy: Monoidal Categories for Active Inference"
https://discopy.org/
In a recent line of work, Tull, Kleiner & Smithe have proposed category theory as a foundational framework for predictive processing and active inference. In particular, string diagrams provide a graphical representation for describing how the free energy of an agent can be described as the composition of the free energies of its parts. We argue that the same string diagrams can also be used as the underlying data structure for a modular implementation of active inference. We then give a demo of DisCoPy, the Python library for computing with string diagrams, and discuss its potential as a toolkit for the active inference practitioner.

Active Inference Institute information:
Website: https://www.activeinference.institute/
Activities: https://activities.activeinference.institute/
Discord: https://discord.activeinference.institute/
Donate: http://donate.activeinference.institute/
YouTube: https://www.youtube.com/c/ActiveInference/
X: https://x.com/InferenceActive
Active Inference Livestreams: https://video.activeinference.institute/