AI Archaeology – Reading Ancient Texts With AI – C. Handmer, J. Schilliger, Y. Nader

Archaeology: Reading Ancient Texts With Cutting Edge Technology
Recent advances in artificial intelligence and computation have enabled an impossible feat dreamed about for thousands of years – the recovery of lost texts from antiquity. In this talk, we will describe how a library destroyed in the famous eruption of Mount Vesuvius is on track to being understood after 1700 years underground and 270 years of mostly failed attempts. Combining high resolution synchrotron X-ray CT scanning and a race to develop software, the effort yielded thousands of characters on Epicurean philosophy, with the promise of millions more to come.

About the speakers:
Casey Handmer is the founder of Terraform Industries, a company building synthetic natural gas from sunlight and air. He has worked on optics, gravitation, magnetic machinery, astrophysics, GPS, planetary mapping, and scrolls.

Julian Schilliger is a Digital Archeologist. Digital archeology started for him as a balance during his studies at ETH Zurich (BSc Computer Science, MSc Robotics) and became a full-time job after winning the Vesuvius Challenge. He develops software that restores CT scans of ancient, rolled-up scrolls. He enjoys working with visual computing, machine learning and algorithms of all kinds. He develops new algorithms most efficiently outdoors in nature, for example on a hike.

Youssef Nader is an Egyptian computer scientist and a PhD student at the Freie University of Berlin, working on explainable AI and self-supervised learning. In 2023, Youssef led the Vesuvius Grand Prize winning team and developed 3D image segmentation models capable of retrieving more than 2,000 characters from ancient burnt scrolls.

Frühere Post zum Thema KI

• Höchst faszinierend: KI rekonstruiert bisher unbekannten Text aus verkohlten Papyri (11.2.2024)
• Verkohlte Schriftrollen: KI macht das Unlesbare lesbar (15.10.2023)