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
The key to geckos’ unrivalled climbing skills isn’t sticky feet. It’s subatomic
Technology and the self
Greetings from Green Bank – the small town where modern technology is banned
Far from frivolous, cuteness is a powerful – and still mysterious – force of nature
Dance and theatre
How a Noh mask-maker summons a lifelike face from a single block of wood
The ancient world
What wine vessels reveal about politics and luxury in ancient Athens and Persia
David Goldblatt captured the contradictions of apartheid in stark black and white
In the search for life, might alien ocean worlds be a better bet than Earth-like planets?
Thinkers and theories
Is simulation theory a way to shirk responsibility for the world we’ve created?
A dazzling slice-by-slice exploration of wood exposes hidden patterns and hues