Predicting the past with deep neural networks
Ancient history relies on disciplines such as epigraphy for evidence of the thought, language, society and history of past civilizations. However, over the centuries, many inscriptions have been damaged to the point of illegibility, transported far from their original location and their date of writing is steeped in uncertainty. To address these challenges we present Ithaca, a deep neural network for the textual restoration, geographical attribution and chronological attribution of ancient Greek inscriptions. The goal of this presentation is to demonstrate how recent advances in the field of Deep Learning can assist and expand a historian’s workflow, and highlight the importance of joint interdisciplinary research.

medieval.ox.ac.uk/2023/01/28/predicting-the-past-with-deep-neural-networks
Date: 1 February 2023, 17:00 (Wednesday, 3rd week, Hilary 2023)
Venue: The Queen's College, High Street OX1 4AW
Venue Details: Memorial Room at The Queen’s College
Speaker: Yannis Assael (Google DeepMind)
Organiser: Oxford Medieval Studies
Booking required?: Not required
Audience: Public
Editor: Coral Kim