Categories for Artificial General Intelligence
A detailed introduction to the application of category theory to formulate a research program in artificial general intelligence.
Explore the book →The categorical AI series
Four books. One categorical research program.
A completed four-volume arc from functorial models of cognition and learning by structural repair to infinitesimal creativity and the discovery of compositional worlds.
Machine Learning from Enforcing Compositionality
A novel formulation of machine learning, based not on minimizing loss functions, but driven by failures of compositionality.
Explore the book →
Infinitesimal Creativity
A novel framework for modeling creativity as a double involution over assimilation of experience and accommodation through theory augmentation.
Explore the book →
Discovering Compositional Worlds from Interaction
A categorical theory of how lifelong learners identify doctrines, build world models from interaction, and repair them when their structural assumptions fail.
Explore the book →Earlier books
Representation, learning, and robotics
Earlier work on representation discovery, reinforcement learning, and learning in autonomous systems.
Representation Discovery in Markov Decision Processes and Reinforcement Learning
Publisher page →
An Introduction to Representation Discovery
Publisher page →