UMass Amherst · Graduate Seminar · Spring 2026

COMPSCI 692CT — Category Theory for AGI

Meets Mon/Wed 5:30–6:45pm ET · Online (live & recorded) · Instructor: Sridhar Mahadevan · Zoom link TBA

What is this course about?

The world's largest AI companies are collectively spending several trillion dollars in the most expensive race in human history to build artificial general intelligence (AGI). This course will give students a detailed introduction to category theory, and how to use it to analyze today’s AGI systems, understand their limitations and how to design the next generation of AGI sytems. We’ll cover the core theoretical concepts, including categories, functors, natural transformations, the Yoneda lemma, limits & colimits, adjunctions, monads, and Kan extensions, as well as their application to building AGI systems that can reason causally, learn from their experience, plan to achieve long-term goals, interact with users in natural language, and ultimately, achieve consciousness.

Texts

Tentative weekly outline

WeekCategory Theory FocusAGI Modality
W1Categories & FunctorsCompositional Machine Learning
W2Natural Transformations & Yoneda LemmaUniversal Imitation Games
W3Limits & ColimitsBuilding compositional structures(pullbacks/pushouts)
W4AdjunctionsBridging Causal and Statistical Learning
W5MonadsCategorical Probability and Disintegration
W6Symmetric Monoidal CategoriesMarkov Categories and string diagrams
W7Topos TheoryNew Architectures for LLMs
W8Presheaves & Internal Logic (Ω)Reasoning in possible worlds
W9Topos Causal Models IInterventions as Subobject Clasifiers
W10Kan ExtensionsLearning to Extend Functors
W11Coalgebras & CoinductionUniversal Reinforcement Learning
W12Simplicial SetsUMAP and manifold learning
W13Compositional GamesEquilibria via variational inequalities
W14Consciousness And Student Project DemosFrontiers of AGI

This outline will evolve; readings and Zoom link will appear here.

Contact

Instructor: Sridhar Mahadevan · Email: mahadeva@cs.umass.edu

© 2026 UMass Amherst · COMPSCI 692CT