Get curated editors’ picks, peeks behind the scenes, film recommendations and more.
Ancient stone inscriptions offer some of the most powerful primary sources available to historians. However, as these stones are often many thousands of years old, and thus eroded, chipped or otherwise compromised, they can also be immensely difficult to translate, as well as to place in time and space. With this important challenge in mind, Thea Sommerschield, a historian, and Yannis Assael, an artificial intelligence research scientist, teamed up to create Ithaca – a deep neural network that helps to date, place and translate ancient text. Working from a database of 80,000 ancient Greek inscriptions, the neural network combines its sophisticated understanding of patterns to predict missing words and offer guesses as to when and where a text was written. Worth noting too that, while the program fills in the blanks much better than historians working independently of the technology, it was at its most accurate when collaborating with a human expert.
Video by Nature
Producer: Shamini Bundell
video
Death
Even in modern secular societies, belief in an afterlife persists. Why?
9 minutes
video
Nature and landscape
Take a serene hike through an ancient forest, inspired by a Miyazaki masterpiece
6 minutes
video
Design and fashion
The mundane becomes mesmerising in this deep dive into segmented displays
14 minutes
video
Physics
A song of ice, fire and jelly – exploring the physics and history of the trumpet
9 minutes
video
Architecture
Tour the European architecture that dreamed of a wondrous, fictitious China
16 minutes
video
Spirituality
Trek alongside spiritual pilgrims on a treacherous journey across Pakistan
6 minutes
video
Thinkers and theories
Photographs offer a colonialist window to the past – one that must be challenged
14 minutes
video
Animals and humans
An artist and ants collaborate on an exhibit of ‘tiny Abstract Expressionist paintings’
5 minutes
video
Mathematics
How a curious question about colouring maps changed mathematics forever
9 minutes