Categorical AI trilogy
Categories for Artificial General Intelligence
A detailed introduction to the application of category theory to formulate a research program in artificial general intelligence.
Read the digital edition ↗Books
Books as evolving research programs.
The newest trilogy is published as a set of open digital drafts, designed to remain corrigible as the theory, experiments, and community develop. Earlier books document the path that led there.
Categorical AI trilogy
Machine Learning from Enforcing Compositionality
A novel formulation of machine learning, based not on minimizing loss functions, but driven by failures of compositionality.
Read the digital edition ↗
Categorical AI trilogy
Infinitesimal Creativity
A novel framework for modeling creativity as a double involution over assimilation and accommodation.
Read the digital edition ↗Earlier books
Foundations of the trajectory
Representation Discovery using Harmonic Analysis
A geometric and spectral account of representation discovery in machine learning.
Multiagent Learning
Foundations and algorithms for learning in systems with multiple interacting agents.
Robot Learning and Learning Apprenticeship
Early work on autonomous agents, imitation, apprenticeship, and learning from structured experience.