ARTHIST 289S
Artificial Intelligence and the Past
Maurizio Forte
Description from DukeHub
Machine learning now reconstructs ruined buildings, reads damaged inscriptions, sorts millions of excavation photographs, and generates images of places no one has seen. What kind of knowledge is that? Students work with real archaeological datasets, Etruscan sites, Neolithic wall paintings, museum collections, to test what these systems can and cannot establish about the past. Topics include generative reconstruction, computer vision, provenance and looted antiquities, and the ethics of plausible but unverifiable images. No technical background required.
Skills
- ai and machine learningtitle: "artificial intelligence"
- makingdescription: "photographs" and 1 more
AI-resilient: 3 of 5
- No: Physical, lab or field work
- No: Live work with people
- Yes: Judgment someone is accountable for · "ethics"
- Yes: A craft you practice with your hands or body · "photographs"
- Yes: Small, in-person format · seminar, 16 seats per section
The checks lean on Microsoft Research, Working with AI (2025), which found generative AI applies least to physical work and hands-on work with people. A signal, not a promise. How the score works
More in ARTHIST
- Conquering the Cosmos: The Art and Visual Culture of the Space Race ARTHIST 106CNS
- The Archaeology of Death: Ritual and Social Structure in the Ancient World ARTHIST 143S
- Museum Theory and Practice ARTHIST 220
- Arts Policy, Leadership, and Engagement ARTHIST 228
- Japanese Architecture ARTHIST 234
- Science Fiction Film ARTHIST 238S