AAAI Fellow

Co-Director, Autonomous Learning Laboratory

Artificial Intelligence

Category Theory

Machine Learning

Universal Representations

firstname.i.lastname AT gmail

Administrative Assistant: Sarah Byrne

My current research involves applying category theory to AI. Categories are defined by objects, arbitrary entities whose interactions through a collection of morphisms defines them. Universal representations of objects emerge from analyzing their interactions. Universal AI provides new ways to model the core components of intelligence: adaptation, causality, communication, creativity, decision making, and perception. See my recent invited talks or papers listed below for details.

Recent Preprints and Invited Talks

Sridhar Mahadevan, Universal Representations for AI, Invited Talk, Department of Computer Science, Oregon State University, September 23rd, 2022

Sridhar Mahadevan, Unifying Causal Inference and Reinforcement Learning using Higher-order Category Theory, Arxiv, September 2022

Sridhar Mahadevan, Categoroids: Universal Conditional Independence, Arxiv, July 2022

Sridhar Mahadevan, On the Universality of Causal Diagrams and the Causal Reproducing Property, Arxiv, July 2022

Sridhar Mahadevan, Universal Decision Models , Invited Talk, Indian Institute of Science, October 23rd, 2021

Sridhar Mahadevan, Universal Decision Models, Arxiv, 2021

Sridhar Mahadevan, Causal Homotopy, Arxiv, 2021.

Sridhar Mahadevan, Causal Inference in Network Economics, Arxiv, 2021.

---