Dynamic programming is a class of algorithms used to compute optimal control policies for
Markov decision processes. Dynamic programming is ubiquitous in control theory, and is also …

We show that several major algorithms of reinforcement learning (RL) fit into the framework
of categorical cybernetics, that is to say, parametrised bidirectional processes. We build on …

This live demonstration showcases a cyber-physical system tailored for inexpensive remote
bird monitoring. A comprehensive analysis of the application requirements along with a tight …

OBJECTIVES: The application of repair techniques to treat mitral valve incompetence has
increased progressively during the past 20 years. Unfortunately, recent reports have …

In the modern era, the birdnests are threatened by industrialisation, deforestation and pollution.
Birdnests are a major part of a bird’s life because birdnests provide a comfortable zone …

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 …

Bayes' rule tells us how to invert a causal process in order to update our beliefs in light of
new evidence. If the process is believed to have a complex compositional structure, we may …

In this survey, we provide an overview of category theory-derived machine learning from four
mainstream perspectives: gradient-based learning, probability-based learning, invariance …