Skip to main content

The AI Historian – Teaching Machines to Understand the Past

Supervisor

Suitable for

MSc in Advanced Computer Science
Computer Science, Part C
Computer Science, Part B

Abstract

Background Reading:

https://www.engineegroup.com/tcsit/article/view/TCSIT-7-148

https://proceedings.neurips.cc/paper_files/paper/2024/hash/38cc5cba8e513547b96bc326e25610dc-Abstract-Datasets_and_Benchmarks_Track.html

https://openreview.net/pdf?id=EO8mTLqDuT

https://openreview.net/pdf?id=EDWTHMVOCj

https://www.amazon.co.uk/Causality-Judea-Pearl/dp/052189560X

 

How can we build an artificial intelligence that thinks like a historian?
This project will develop AI systems that can interpret historical evidence — texts, maps, artefacts, and data — to test causal explanations for how societies evolve, collapse, and endure. Students will work at the intersection of machine learning, causal inference, simulation, and digital history, developing methods that let AI reason about events, uncertainty, and human behaviour across time. Collaborations with anthropologists and historians at Oxford (including the Seshat and CSSC teams) offer unique access to structured historical datasets. Ideal applicants have strong technical skills in AI/ML or simulation and curiosity about applying them to the grand questions of human history.