Rethinking AI: From Functions to Functors
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (46) · 39737-39744
DOI: 10.1609/aaai.v40i46.41329 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Sridhar Mahadevan. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
We propose a new theoretical foundation for artificial intelligence (AI) and machine learning (ML), building on ideas in pure mathematics relating to categories and functors. This paper builds on our AAAI 2025 tutorial Thinking with Functors: Category Theory for A(G)I, which provides background material. In addition, our recent papers on intuitionistic j-do calculus in Topos Causal Models} and GAIA: Categorical Foundations of Generative AI, illustrate how to generalize well-known formalisms in AI, such as causal inference and deep learning, to a category-theoretic setting.
Zitieren
APA
Mahadevan, S. (2026). Rethinking AI: From Functions to Functors. Proceedings of the AAAI Conference on Artificial Intelligence, 40(46), 39737-39744. https://doi.org/10.1609/aaai.v40i46.41329
Vancouver
Mahadevan S. Rethinking AI: From Functions to Functors. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(46):39737-39744. doi:10.1609/aaai.v40i46.41329
BibTeX
@article{Mahadevan2026,
author = {Mahadevan, Sridhar},
title = {Rethinking AI: From Functions to Functors},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {46},
pages = {39737--39744},
doi = {10.1609/aaai.v40i46.41329}
}
EUVIMED