- The Vesuvius Challenge aims to decipher content from two millennia-old scrolls preserved in a villa covered by the Vesuvius eruption in 79 AD;<\/li>
- Using cutting-edge technologies, participants have until the end of 2023 to read four passages from the scrolls, with a $700,000 grand prize at stake.<\/li><\/ul><\/div>\n\n\n\n
Launched by former GitHub CEO Nat Friedman, the Vesuvius Challenge<\/a> is pushing its contestants to decipher the content of some of the two millennia-old scrolls found in the villa using today\u2019s cutting-edge technologies. Despite almost two thousand years passing by, the papyri are still intact. The volcanic debris\u2019 heat carbonized them, but they stayed preserved underground. \u201cIt\u2019s very tantalizing because, on the one hand, these papyri have been preserved, but on the other, we can\u2019t read them yet,\u201d says JP Posma, project lead of the Vesuvius Challenge. Its participants have time until the end of 2023 to read four passages and win a $700,000 grand prize. <\/p>\n\n\n\n
\nThis is an article from IO Next: The Year Of…<\/a><\/strong> For the last magazine of this year, we selected the articles that stuck with us the most, whether it was an impressive interview, an important story or just something funny.<\/strong><\/p>\n<\/div>
![\"\"](\"https:\/\/archive.ioplus.nl\/wp-content\/uploads\/2023\/12\/Schermafbeelding-2023-12-11-114944-732x1004.png\")
<\/figure><\/div>\n\n\n\nWhy Mauro chose to write a follow-up on this article:\u00a0<\/h2>
Discovering more about our past isn’t the use case that immediately pops up when thinking about AI. But AI is a horizontal technology, finding applications in all spaces, historical research included. AI is proving to be good at knowing more about our ancestors, as participants of the Vesuvius challenge started to decipher two thousands-year-old papyri with the help of machine learning algorithms.<\/p><\/div>\n\n\n\n
Reading the first words <\/h2>\n\n\n\n
The challenge<\/a> builds on a series of discoveries by Dr. Brent Seales<\/a>‘ lab at the University of Kentucky. In early 2023, their machine-learning model recognized ink from X-ray scans of the papyri. Piece by piece, we are starting to read the content of the manuscripts. Luke Farritor, a computer science student, was the first contestant to read an entire word \u2013 precisely \u03c0\u03bf\u03c1\u03c6\u03cd\u03c1\u03b1c, the ancient Greek word for purple \u2013 from the scroll, winning the $40,000 first-letter prize. Shortly after, Youssef Nader, a Ph.D. student at the Free University of Berlin, discovered the same word with more precise results, bagging the second-place award. <\/p>\n\n\n\n
\u201cI was thrilled and excited to the point of being nervous. It\u2019s also a competition, so I couldn\u2019t share this with many people. I was also still trying to be skeptical not to overestimate it. I redid the experiments a couple of times to validate my method, then I reached out to JP, and he urged me to submit the result as soon as possible,\u201d told Innovation Origins Nader. <\/p>\n\n\n\n
![\"\"](\"https:\/\/archive.ioplus.nl\/wp-content\/uploads\/2023\/12\/Ontwerp-zonder-titel-9-1004x815.png\")
The deciphered word – \u00a9 Vesuvius Challenge<\/figcaption><\/figure>\n\n\n <\/a><\/div><\/div>Unearthing Pompeii’s secrets with cutting-edge technology<\/div>\u201cAt about one in the afternoon, my mother pointed out a cloud with an odd size and appearance that had just formed. From that distance, it was not clear from which mountain the cloud was rising, although it was found afterward to be Vesuvius.\u201d<\/div><\/div><\/div>\n\n\nFlashback<\/h2>\n\n\n\n
The papyrus villa was first discovered in 1750 when a farmer dug a well, and stumbled across its marble pavement. Archeological research followed suit, recovering many scrolls over the decades. In 2015, Seales lab’s first breakthrough happened. The scientists read the En Gedi scroll \u2014 an ancient Hebrew parchment found in the Dead Sea \u2013 combining X-ray scans \u2014 through computer tomography, CT \u2013 and computer vision technologies. Therefore, the desire came to apply the same technique to the Herculaneum Papyri, too.<\/p>\n\n\n\n
Four years later, the American researchers used a particle accelerator to scan two of the scrolls retrieved in the villa. Thanks to this experiment, they inferred that machine learning models could recognize surface patterns indicating ink presence. And that became a reality at the beginning of 2023 when their model detected ink on the scans. So the challenge followed. <\/p>\n\n\n\n
A 3D reproduction of the scroll<\/h2>\n\n\n\n
No different than in hospital CT scans, X-rays are sent through the object \u2013 the scroll in this case \u2013 getting a picture on the opposite side. \u201cBut then, one can rotate the object to get many pictures from different angles. Through tomography, one can reconstruct a 3D image from all those pictures,\u201d explains Posma.<\/p>\n\n\n\n
Particle accelerators can help get high-resolution images, as they can provide a high-quality energy source and specific light incidences. At this point, the scroll content appears in a conglomerate of voxels, the name for the data points in a 3D grid. From there, it\u2019s easier for AIto identify characters and read them. The idea is to develop neural networks trained on tiny bits of the scroll with and without ink. \u201cThen it\u2019s about inferring patterns and eventually showing some characters,\u2019\u2019 underlines Posma.<\/p>\n\n\n\n
Data models become teachers<\/h2>\n\n\n\n
That\u2019s what Nader did. Specifically, he took the challenge as a chance to experiment with self-supervised learning, one of the latest trends in AI technology, which he combined with his idea to make a data model teacher for another data model. <\/p>\n\n\n\n
In other words, this method trains models based on the information retrieved by a previous model. The first letter detected by one of Nader\u2019s models was a \u2018pi\u2019 (\u03a0), which was then passed to the next model, which improved based on the pre-acquired knowledge. \u201cAfter the next models are trained, they become teachers. And it’s like an ongoing cycle until you get a good amount of data from within the scrolls of ink signals, all of them,\u201d clarifies Nader. <\/p>\n\n\n\n
\u201cThe model takes a small part of the image and tries to predict whether or not there is ink. It trains on with whatever data you have and makes predictions on the new segments from the scrolls,\u201d the Ph.D. student goes on to explain. <\/p>\n\n\n
<\/a><\/div><\/div>AI system self-organises to develop features of brains of complex organisms<\/div>Cambridge scientists have shown that placing physical constraints on an artificially-intelligent system allows it to develop features of the brains of complex organisms in order to solve tasks.<\/div><\/div><\/div>\n\n\nCooperative effort<\/h2>\n\n\n\n
With a computer engineering background and a master\u2019s in data science, Nader is starting his Ph.D. research. With a strong passion for machine learning, the Vesuvius Challenge is not the first one he has participated in. \u201cThe historical aspect of it is exciting, and prize money doesn’t hurt the interest either. It\u2019s a tough problem that makes for a very nice playground for testing ideas and trying things,\u201d he says. <\/p>\n\n\n\n
Despite all the efforts made by the University of Kentucky team, many still needed the collective power of many to decipher the scrolls, as per Posma. The Vesuvius Challenge is a competition, but it also created a community where participants come together \u2013 on a server of the messaging app Discord \u2013 to discuss ways to solve the puzzle. Moreover, both the codes developed by Farritor and Nader were made public to the other contestants. After a period without relevant advancements, the two submissions raised the community’s spirits, pushing which the research forward. <\/p>\n\n\n\n
Completing the challenge<\/h2>\n\n\n\n
With about a month remaining until the end of the competition, there are still chances to read the four tweets from the past \u2013 each passage is about 140 characters long. \u201cI think it\u2019s in the realm of possibilities. It\u2019s still unclear whether there is enough text to be recoverable or maybe it\u2019s too damaged. This is still a point of debate, and it will be the work of the next few weeks to try and see if there\u2019s a possibility,\u201d sums up Nader. <\/p>\n","protected":false},"excerpt":{"rendered":"
\u201cAt about one in the afternoon, my mother pointed out a cloud with an odd size and appearance that had just formed. From that distance, it was unclear from which mountain the cloud was rising, although it was found afterward to be Vesuvius.\u201d That\u2019s how the historian Pliny the Younger described \u2013 in a letter […]<\/p>\n","protected":false},"author":2084,"featured_media":494947,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"advgb_blocks_editor_width":"","advgb_blocks_columns_visual_guide":"","footnotes":""},"categories":[8553],"tags":[75599,79270,82742,77777],"location":[76794],"article_type":[36684],"serie":[],"archives":[],"internal_archives":[],"reboot-archive":[],"class_list":["post-464792","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-digital","tag-75599","tag-2023-ai","tag-pompeii","tag-vesuvius-challenge","location-united-states","article_type-news"],"blocksy_meta":[],"acf":{"subtitle":"The Vesuvius Challenge involves its participants reading two-millennia-old scrolls with AI. The first words are starting to be deciphered. ","text_display_homepage":false},"author_meta":{"display_name":"Mauro Mereu","author_link":"https:\/\/ioplus.nl\/archive\/author\/mauro-mereu\/"},"featured_img":"https:\/\/ioplus.nl\/archive\/wp-content\/uploads\/2023\/12\/innovationorigins_Pompeii_with_an_exploding_vulcano_in_the_back_4b3183fd-fd92-4dac-a152-8f6e6cc1ebe0.png","coauthors":[],"tax_additional":{"categories":{"linked":["Digital<\/a>"],"unlinked":["Digital<\/span>"]},"tags":{"linked":["2023<\/a>","2023 AI<\/a>","Pompeii<\/a>","Vesuvius Challenge<\/a>"],"unlinked":["2023<\/span>","2023 AI<\/span>","Pompeii<\/span>","Vesuvius Challenge<\/span>"]}},"comment_count":"0","relative_dates":{"created":"Posted 2 years ago","modified":"Updated 2 years ago"},"absolute_dates":{"created":"Posted on December 28, 2023","modified":"Updated on December 28, 2023"},"absolute_dates_time":{"created":"Posted on December 28, 2023 8:00 am","modified":"Updated on December 28, 2023 8:00 am"},"featured_img_caption":"","series_order":"","_links":{"self":[{"href":"https:\/\/ioplus.nl\/archive\/wp-json\/wp\/v2\/posts\/464792","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ioplus.nl\/archive\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/ioplus.nl\/archive\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/ioplus.nl\/archive\/wp-json\/wp\/v2\/users\/2084"}],"replies":[{"embeddable":true,"href":"https:\/\/ioplus.nl\/archive\/wp-json\/wp\/v2\/comments?post=464792"}],"version-history":[{"count":0,"href":"https:\/\/ioplus.nl\/archive\/wp-json\/wp\/v2\/posts\/464792\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/ioplus.nl\/archive\/wp-json\/wp\/v2\/media\/494947"}],"wp:attachment":[{"href":"https:\/\/ioplus.nl\/archive\/wp-json\/wp\/v2\/media?parent=464792"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/ioplus.nl\/archive\/wp-json\/wp\/v2\/categories?post=464792"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/ioplus.nl\/archive\/wp-json\/wp\/v2\/tags?post=464792"},{"taxonomy":"location","embeddable":true,"href":"https:\/\/ioplus.nl\/archive\/wp-json\/wp\/v2\/location?post=464792"},{"taxonomy":"article_type","embeddable":true,"href":"https:\/\/ioplus.nl\/archive\/wp-json\/wp\/v2\/article_type?post=464792"},{"taxonomy":"serie","embeddable":true,"href":"https:\/\/ioplus.nl\/archive\/wp-json\/wp\/v2\/serie?post=464792"},{"taxonomy":"archives","embeddable":true,"href":"https:\/\/ioplus.nl\/archive\/wp-json\/wp\/v2\/archives?post=464792"},{"taxonomy":"internal_archives","embeddable":true,"href":"https:\/\/ioplus.nl\/archive\/wp-json\/wp\/v2\/internal_archives?post=464792"},{"taxonomy":"reboot-archive","embeddable":true,"href":"https:\/\/ioplus.nl\/archive\/wp-json\/wp\/v2\/reboot-archive?post=464792"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}