{"id":6435,"date":"2023-10-13T20:08:01","date_gmt":"2023-10-13T20:08:01","guid":{"rendered":"https:\/\/dailyai.com\/?p=6435"},"modified":"2024-03-28T00:42:02","modified_gmt":"2024-03-28T00:42:02","slug":"machine-learning-reveals-the-contents-of-ancient-scrolls-and-stone-tablets","status":"publish","type":"post","link":"https:\/\/dailyai.com\/da\/2023\/10\/machine-learning-reveals-the-contents-of-ancient-scrolls-and-stone-tablets\/","title":{"rendered":"Maskinl\u00e6ring afsl\u00f8rer indholdet af gamle skriftruller og stentavler"},"content":{"rendered":"

Luke Farritor, en 21-\u00e5rig datalogistuderende fra University of Nebraska-Lincoln, har afsl\u00f8ret teksten i en forkullet skriftrulle fra det gamle Herculaneum.\u00a0<\/b><\/p>\n

Denne rulle har v\u00e6ret ul\u00e6selig siden vulkanudbruddet i \u00e5r 79 e.Kr., som ogs\u00e5 opslugte Pompeji. Farritors maskinl\u00e6ringsalgoritme lokaliserede gr\u00e6ske bogstaver p\u00e5 den sammenrullede papyrus, herunder ordet \u03c0\u03bf\u03c1\u03d5\u03c5\u03c1\u03b1\u03c2 (porphyras), som betyder 'lilla'.\u00a0<\/span><\/p>\n

Hans teknik gik ud p\u00e5 at identificere sm\u00e5, nuancerede forskelle i overfladeteksturen for at tr\u00e6ne sit neurale netv\u00e6rk til at opdage bl\u00e6k og dermed leterring.\u00a0<\/span><\/p>\n

\"Da jeg s\u00e5 det f\u00f8rste billede, blev jeg chokeret\". <\/span>sagde<\/span><\/a> Federica Nicolardi, en papyrolog fra universitetet i Napoli. \"Det var s\u00e5dan en dr\u00f8m,\" fortsatte hun, \"jeg kan faktisk se noget fra indersiden af en skriftrulle.\"<\/span><\/p>\n

Rullerne, som blev begravet af Vesuvs udbrud i 79 e.Kr., har v\u00e6ret stort set utilg\u00e6ngelige p\u00e5 grund af deres skr\u00f8belige tilstand.\u00a0<\/span><\/p>\n

N\u00e5r man manuelt ruller de forkullede ruller ud, falder de fra hinanden, hvilket fik de l\u00e6rde til at frygte, at indholdet ville forblive et mysterium for evigt.\u00a0<\/span><\/p>\n

\"AI-rulle\"
En forkullet rulle fra Herculaneum, der ikke kan rulles ud. Kilde: Naturen<\/a>.<\/figcaption><\/figure>\n

Som Nicolardi forklarede: \"Det er s\u00e5 sk\u00f8re objekter. De er alle sammen kr\u00f8llede og knuste.\"<\/span><\/p>\n

I erkendelse af udfordringen med at dechifrere rullerne blev <\/span>Vesuvius-udfordringen<\/span><\/a> blev oprettet med forskellige priser, herunder en hovedpr\u00e6mie p\u00e5 US$700.000 for at dechifrere flere passager fra en skriftrulle.<\/span><\/p>\n

Den 12. oktober blev det offentliggjort, at Farritor havde vundet en pr\u00e6mie p\u00e5 $40.000 for at have identificeret over 10 tegn i et lille udsnit af papyrussen.\u00a0<\/span><\/p>\n

En anden deltager, Youssef Nader fra Freie Universit\u00e4t Berlin, modtog $10.000 for sin andenplads.<\/span><\/p>\n

Historikeren Thea Sommerschield, som besk\u00e6ftiger sig med det antikke Gr\u00e6kenland og Rom, beskriver det som \"ekstremt sp\u00e6ndende\", at man nu endelig kan se bogstaver og ord i rullerne.\u00a0<\/span><\/p>\n

Sommerschield n\u00e6vnte, at fortolkningen af disse kunne \"revolutionere vores viden om oldtidens historie og litteratur\" fra regionen.\u00a0<\/span><\/p>\n

Det er ikke f\u00f8rste gang, at forskere har fors\u00f8gt at l\u00e6se disse gamle karboniserede skriftruller. I 2019 fors\u00f8gte Brent Seales, professor i datalogi med speciale i virtuel l\u00e6sning og bevaring af gamle skriftruller, at \"pakke skriftrullerne virtuelt ud\" ved hj\u00e6lp af r\u00f8ntgencomputertomografi-scanninger (CT).\u00a0<\/span><\/p>\n

I 2016 lykkedes det Seales med et gammelt hebraisk pergament, der blev fundet i 1970 i Ein Gedi i Israel, at afsl\u00f8re dele af Tredje Mosebog.\u00a0<\/span><\/p>\n

Men Herculaneum-rullerne udgjorde en anden udfordring: Bl\u00e6kket, der var lavet af tr\u00e6kul og vand, stod ikke frem i scanningerne.<\/span><\/p>\n

Det var her, Farritor fik succes ved at fokusere p\u00e5 en specifik subtil tekstur, kaldet \"krakelering\", for spor af bl\u00e6k.\u00a0<\/span><\/p>\n

Farritor sagde: \"Jeg hoppede op og ned\", da hans algoritme afsl\u00f8rede fem bogstaver fra et nyligt udgivet segment. \"Du godeste, det her kommer faktisk til at virke,\" inds\u00e5 han.\u00a0<\/span><\/p>\n

Kort tid efter forfinede han sin model og identificerede de n\u00f8dvendige ti bogstaver til prisen, hvor ordet 'purpur' ikke tidligere var identificeret i Herculaneum-rullerne.<\/span><\/p>\n

Hovedpr\u00e6mien i Vesuvius Challenge er endnu ikke afsl\u00f8ret, og fristen er sat til den 31. december.\u00a0<\/span><\/p>\n

AI til afkodning af gamle sprog<\/span><\/h2>\n

For seks \u00e5rtusinder siden bosatte sumererne sig i Mesopotamien, landet der str\u00e6kker sig over floderne Tigris og Eufrat.\u00a0<\/span><\/p>\n

Denne region, der d\u00e6kker det nuv\u00e6rende Irak, Kuwait, Tyrkiet og Syrien, var vidne til udviklingen fra sm\u00e5 landbrugssamfund til store bycivilisationer. Byer som Uruk blomstrede op og integrerede indviklede kanaler, vandingsanl\u00e6g og styringscentre. Det var en kritisk \u00e6ra for menneskehedens fremskridt og udvikling.\u00a0<\/span><\/p>\n

Sumererne skrev med en skrift, der kaldes kileskrift. Dette skriftsystem kr\u00e6vede, at man pressede siv ned i ler, hvilket skabte komplekse logo-syllabiske inskriptioner. Kileskrift er ikke et sprog - det er en skrift, der omfatter omkring 15 sprog gennem tre \u00e5rtusinder.<\/span><\/p>\n

\"Kileskrift
Et eksempel p\u00e5 en kileskrifttavle, der indeholder en tekst kaldet \"Hymne til Marduk\". Kilde: Wikimedia Commons<\/a>.<\/figcaption><\/figure>\n

Mens kileskrift prim\u00e6rt blev brugt som administrativt v\u00e6rkt\u00f8j til f.eks. at registrere husdyr eller transaktioner, opstod der omkring 2700 f.Kr. en lang r\u00e6kke mere filosofiske og kreative skrifter.\u00a0<\/span><\/p>\n

Et af de mest bem\u00e6rkelsesv\u00e6rdige af disse skrifter er <\/span>Gilgamesh-eposet<\/span><\/a>som str\u00e6kker sig over tolv tavler.<\/span><\/p>\n

Enrique Jim\u00e9nez fra Ludwig Maximilians University i M\u00fcnchen siger: \"Halvdelen af menneskehedens historie er indkapslet i disse kileskrifttavler.\"\u00a0<\/span><\/p>\n

Men kun 75 personer, if\u00f8lge <\/span>New Scientist<\/span><\/a>kan afkode kileskrift p\u00e5 trods af titusindvis af uoversatte tavler verden over.<\/span><\/p>\n

Maskinl\u00e6ring hj\u00e6lper nu forskere med at opklare de historier, der er indgraveret i stentavler, og hj\u00e6lper dem med at udfylde huller og ordne teksterne kronologisk for at finde ud af mere om, hvordan de gamle sumerere levede.\u00a0<\/span><\/p>\n

Maskinl\u00e6ringens rolle i dekryptering af gamle tekster<\/span><\/h2>\n

Enrique Jim\u00e9nez og hans team har grundlagt <\/span>Elektronisk babylonisk litteratur,<\/span><\/a>\u00a0et samarbejde mellem ark\u00e6ologer, dataforskere og historikere.<\/span><\/p>\n

For at analysere kileskrifttavler brugte teamet en maskinl\u00e6ringsteknik, der oprindeligt var designet til sammenligning af gensekvenser. Denne AI forudsiger indholdet af manglende sektioner og gr\u00e6nserne for, hvorn\u00e5r fragmenter passer sammen.<\/span><\/p>\n

Denne teknik f\u00f8rte til opdagelser som manglende dele af Gilgamesh-eposet og en nyopdaget mesopotamisk genre, der beskriver p\u00e6dagogiske parodier og vittigheder for b\u00f8rn.\u00a0<\/span><\/p>\n

I 2020 en separat model, <\/span>DeepScribe<\/span><\/a>blev tr\u00e6net p\u00e5 6.000 annoterede billeder fra <\/span>Persepolis' bef\u00e6stningsarkiv<\/span><\/a>som angiver ca. 100.000 symboler fra det elamitiske sprog (fra det nuv\u00e6rende Iran), dateret omkring 500 f.Kr.<\/span><\/p>\n

Ved at udnytte ressourcer fra UChicago Research Computing Center tr\u00e6nede Krishnan og Eddie Williams en model, der var i stand til at afkode disse tegn med en imponerende n\u00f8jagtighed p\u00e5 80%.\u00a0<\/span><\/p>\n

Teamet har til hensigt at udvikle DeepScribe til et alsidigt afkodningsv\u00e6rkt\u00f8j, der kan omskoles til andre sprog end elamit.\u00a0<\/span><\/p>\n

\"DeepScribe
DeepScribe fors\u00f8ger at l\u00e6se symboler fra det gamle elamitiske sprog. Kilde: DeepScribe<\/a>.<\/figcaption><\/figure>\n

DeepMind har ogs\u00e5 unders\u00f8gt afkodning af gamle sprog ved hj\u00e6lp af maskinl\u00e6ring - i dette tilf\u00e6lde beskadigede oldgr\u00e6ske tavler. <\/span><\/p>\n

Navngivet <\/span>Ithaca<\/span><\/a>Denne model gendannede tekster med 72% pr\u00e6cision, anslog deres alder inden for tre \u00e5rtier og formodede endda deres oprindelse med 71% n\u00f8jagtighed.\u00a0<\/span><\/p>\n

\"DeepMind
DeepMind Ithaca udfylder hullerne i de fragmenterede gr\u00e6ske tavler. Kilde: DeepMind<\/a>.<\/figcaption><\/figure>\n

Ithacas tr\u00e6ning omfattede 60.000 tekster fra 700 f.Kr. til 500 e.Kr. m\u00e6rket med data om deres tid og sted p\u00e5 tv\u00e6rs af 84 gamle territorier.<\/span><\/p>\n

Krydsfeltet mellem gamle tekster og avanceret AI viser, at selv \u00e5rtusindgamle mysterier ikke er immune over for den moderne teknologis fremskridt.\u00a0<\/span><\/p>\n

Ved at blande det gamle med det nye bevarer forskerne b\u00e5de historien og skaber hidtil ukendte muligheder. <\/span>ark\u00e6ologisk viden.<\/p>\n

Disse gennembrud understreger de ubegr\u00e6nsede muligheder, n\u00e5r vi forener menneskelig nysgerrighed med teknologisk dygtighed, og viser, at der er en ny optik, hvorigennem vi kan se vores kollektive fortids vidundere. <\/span><\/p>","protected":false},"excerpt":{"rendered":"

Luke Farritor, en 21-\u00e5rig datalogistuderende fra University of Nebraska-Lincoln, har afsl\u00f8ret teksten i en karboniseret skriftrulle fra det gamle Herculaneum. Rullen har v\u00e6ret ul\u00e6selig siden vulkanudbruddet i \u00e5r 79 e.Kr., som ogs\u00e5 opslugte Pompeji. Farritors maskinl\u00e6ringsalgoritme lokaliserede med succes gr\u00e6ske bogstaver p\u00e5 den sammenrullede papyrus, herunder ordet \u03c0\u03bf\u03c1\u03d5\u03c5\u03c1\u03b1\u03c2 (porphyras), som betyder 'lilla'. Hans teknik gik ud p\u00e5 at identificere sm\u00e5, nuancerede forskelle i overfladeteksturen for at tr\u00e6ne sit neurale netv\u00e6rk til at opdage bl\u00e6k og dermed ogs\u00e5 leterring. \"Da jeg s\u00e5 det f\u00f8rste billede, blev jeg chokeret,\" siger Federica Nicolardi, en papyrolog fra University of<\/p>","protected":false},"author":2,"featured_media":6442,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[88],"tags":[166,105,143],"class_list":["post-6435","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ethics","tag-computer-vision","tag-machine-learning","tag-natural-language-processing"],"yoast_head":"\nMachine learning reveals the contents of ancient scrolls and stone tablets | DailyAI<\/title>\n<meta name=\"description\" content=\"Luke Farritor, a 21-year-old computer science student from the University of Nebraska\u2013Lincoln, has achieved a breakthrough in revealing the first text inside a carbonized scroll from ancient Herculaneum.\u00a0\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/dailyai.com\/da\/2023\/10\/machine-learning-reveals-the-contents-of-ancient-scrolls-and-stone-tablets\/\" \/>\n<meta property=\"og:locale\" content=\"da_DK\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Machine learning reveals the contents of ancient scrolls and stone tablets | DailyAI\" \/>\n<meta property=\"og:description\" content=\"Luke Farritor, a 21-year-old computer science student from the University of Nebraska\u2013Lincoln, has achieved a breakthrough in revealing the first text inside a carbonized scroll from ancient Herculaneum.\u00a0\" \/>\n<meta property=\"og:url\" content=\"https:\/\/dailyai.com\/da\/2023\/10\/machine-learning-reveals-the-contents-of-ancient-scrolls-and-stone-tablets\/\" \/>\n<meta property=\"og:site_name\" content=\"DailyAI\" \/>\n<meta property=\"article:published_time\" content=\"2023-10-13T20:08:01+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2024-03-28T00:42:02+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/shutterstock_308164922.jpg\" \/>\n\t<meta property=\"og:image:width\" content=\"1000\" \/>\n\t<meta property=\"og:image:height\" content=\"667\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"Sam Jeans\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:site\" content=\"@DailyAIOfficial\" \/>\n<meta name=\"twitter:label1\" content=\"Skrevet af\" \/>\n\t<meta name=\"twitter:data1\" content=\"Sam Jeans\" \/>\n\t<meta name=\"twitter:label2\" content=\"Estimeret l\u00e6setid\" \/>\n\t<meta name=\"twitter:data2\" content=\"6 minutter\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"NewsArticle\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/machine-learning-reveals-the-contents-of-ancient-scrolls-and-stone-tablets\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/machine-learning-reveals-the-contents-of-ancient-scrolls-and-stone-tablets\\\/\"},\"author\":{\"name\":\"Sam Jeans\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/711e81f945549438e8bbc579efdeb3c9\"},\"headline\":\"Machine learning reveals the contents of ancient scrolls and stone tablets\",\"datePublished\":\"2023-10-13T20:08:01+00:00\",\"dateModified\":\"2024-03-28T00:42:02+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/machine-learning-reveals-the-contents-of-ancient-scrolls-and-stone-tablets\\\/\"},\"wordCount\":1049,\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/machine-learning-reveals-the-contents-of-ancient-scrolls-and-stone-tablets\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/10\\\/shutterstock_308164922.jpg\",\"keywords\":[\"Computer vision\",\"machine learning\",\"Natural language processing\"],\"articleSection\":[\"Ethics & Society\"],\"inLanguage\":\"da-DK\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/machine-learning-reveals-the-contents-of-ancient-scrolls-and-stone-tablets\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/machine-learning-reveals-the-contents-of-ancient-scrolls-and-stone-tablets\\\/\",\"name\":\"Machine learning reveals the contents of ancient scrolls and stone tablets | DailyAI\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/machine-learning-reveals-the-contents-of-ancient-scrolls-and-stone-tablets\\\/#primaryimage\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/machine-learning-reveals-the-contents-of-ancient-scrolls-and-stone-tablets\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/10\\\/shutterstock_308164922.jpg\",\"datePublished\":\"2023-10-13T20:08:01+00:00\",\"dateModified\":\"2024-03-28T00:42:02+00:00\",\"description\":\"Luke Farritor, a 21-year-old computer science student from the University of Nebraska\u2013Lincoln, has achieved a breakthrough in revealing the first text inside a carbonized scroll from ancient Herculaneum.\u00a0\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/machine-learning-reveals-the-contents-of-ancient-scrolls-and-stone-tablets\\\/#breadcrumb\"},\"inLanguage\":\"da-DK\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/machine-learning-reveals-the-contents-of-ancient-scrolls-and-stone-tablets\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"da-DK\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/machine-learning-reveals-the-contents-of-ancient-scrolls-and-stone-tablets\\\/#primaryimage\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/10\\\/shutterstock_308164922.jpg\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/10\\\/shutterstock_308164922.jpg\",\"width\":1000,\"height\":667},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/2023\\\/10\\\/machine-learning-reveals-the-contents-of-ancient-scrolls-and-stone-tablets\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/dailyai.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Machine learning reveals the contents of ancient scrolls and stone tablets\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#website\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"name\":\"DailyAI\",\"description\":\"Your Daily Dose of AI News\",\"publisher\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/dailyai.com\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"da-DK\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#organization\",\"name\":\"DailyAI\",\"url\":\"https:\\\/\\\/dailyai.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"da-DK\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/Daily-Ai_TL_colour.png\",\"contentUrl\":\"https:\\\/\\\/dailyai.com\\\/wp-content\\\/uploads\\\/2023\\\/06\\\/Daily-Ai_TL_colour.png\",\"width\":4501,\"height\":934,\"caption\":\"DailyAI\"},\"image\":{\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/logo\\\/image\\\/\"},\"sameAs\":[\"https:\\\/\\\/x.com\\\/DailyAIOfficial\",\"https:\\\/\\\/www.linkedin.com\\\/company\\\/dailyaiofficial\\\/\",\"https:\\\/\\\/www.youtube.com\\\/@DailyAIOfficial\"]},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/dailyai.com\\\/#\\\/schema\\\/person\\\/711e81f945549438e8bbc579efdeb3c9\",\"name\":\"Sam Jeans\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"da-DK\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g\",\"caption\":\"Sam Jeans\"},\"description\":\"Sam is a science and technology writer who has worked in various AI startups. When he\u2019s not writing, he can be found reading medical journals or digging through boxes of vinyl records.\",\"sameAs\":[\"https:\\\/\\\/www.linkedin.com\\\/in\\\/sam-jeans-6746b9142\\\/\"],\"url\":\"https:\\\/\\\/dailyai.com\\\/da\\\/author\\\/samjeans\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Maskinl\u00e6ring afsl\u00f8rer indholdet af gamle skriftruller og stentavler | DailyAI","description":"Luke Farritor, en 21-\u00e5rig datalogistuderende fra University of Nebraska-Lincoln, har opn\u00e5et et gennembrud ved at afsl\u00f8re den f\u00f8rste tekst i en karboniseret skriftrulle fra det gamle Herculaneum.\u00a0","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/dailyai.com\/da\/2023\/10\/machine-learning-reveals-the-contents-of-ancient-scrolls-and-stone-tablets\/","og_locale":"da_DK","og_type":"article","og_title":"Machine learning reveals the contents of ancient scrolls and stone tablets | DailyAI","og_description":"Luke Farritor, a 21-year-old computer science student from the University of Nebraska\u2013Lincoln, has achieved a breakthrough in revealing the first text inside a carbonized scroll from ancient Herculaneum.\u00a0","og_url":"https:\/\/dailyai.com\/da\/2023\/10\/machine-learning-reveals-the-contents-of-ancient-scrolls-and-stone-tablets\/","og_site_name":"DailyAI","article_published_time":"2023-10-13T20:08:01+00:00","article_modified_time":"2024-03-28T00:42:02+00:00","og_image":[{"width":1000,"height":667,"url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/shutterstock_308164922.jpg","type":"image\/jpeg"}],"author":"Sam Jeans","twitter_card":"summary_large_image","twitter_creator":"@DailyAIOfficial","twitter_site":"@DailyAIOfficial","twitter_misc":{"Skrevet af":"Sam Jeans","Estimeret l\u00e6setid":"6 minutter"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"NewsArticle","@id":"https:\/\/dailyai.com\/2023\/10\/machine-learning-reveals-the-contents-of-ancient-scrolls-and-stone-tablets\/#article","isPartOf":{"@id":"https:\/\/dailyai.com\/2023\/10\/machine-learning-reveals-the-contents-of-ancient-scrolls-and-stone-tablets\/"},"author":{"name":"Sam Jeans","@id":"https:\/\/dailyai.com\/#\/schema\/person\/711e81f945549438e8bbc579efdeb3c9"},"headline":"Machine learning reveals the contents of ancient scrolls and stone tablets","datePublished":"2023-10-13T20:08:01+00:00","dateModified":"2024-03-28T00:42:02+00:00","mainEntityOfPage":{"@id":"https:\/\/dailyai.com\/2023\/10\/machine-learning-reveals-the-contents-of-ancient-scrolls-and-stone-tablets\/"},"wordCount":1049,"publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"image":{"@id":"https:\/\/dailyai.com\/2023\/10\/machine-learning-reveals-the-contents-of-ancient-scrolls-and-stone-tablets\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/shutterstock_308164922.jpg","keywords":["Computer vision","machine learning","Natural language processing"],"articleSection":["Ethics & Society"],"inLanguage":"da-DK"},{"@type":"WebPage","@id":"https:\/\/dailyai.com\/2023\/10\/machine-learning-reveals-the-contents-of-ancient-scrolls-and-stone-tablets\/","url":"https:\/\/dailyai.com\/2023\/10\/machine-learning-reveals-the-contents-of-ancient-scrolls-and-stone-tablets\/","name":"Maskinl\u00e6ring afsl\u00f8rer indholdet af gamle skriftruller og stentavler | DailyAI","isPartOf":{"@id":"https:\/\/dailyai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/dailyai.com\/2023\/10\/machine-learning-reveals-the-contents-of-ancient-scrolls-and-stone-tablets\/#primaryimage"},"image":{"@id":"https:\/\/dailyai.com\/2023\/10\/machine-learning-reveals-the-contents-of-ancient-scrolls-and-stone-tablets\/#primaryimage"},"thumbnailUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/shutterstock_308164922.jpg","datePublished":"2023-10-13T20:08:01+00:00","dateModified":"2024-03-28T00:42:02+00:00","description":"Luke Farritor, en 21-\u00e5rig datalogistuderende fra University of Nebraska-Lincoln, har opn\u00e5et et gennembrud ved at afsl\u00f8re den f\u00f8rste tekst i en karboniseret skriftrulle fra det gamle Herculaneum.\u00a0","breadcrumb":{"@id":"https:\/\/dailyai.com\/2023\/10\/machine-learning-reveals-the-contents-of-ancient-scrolls-and-stone-tablets\/#breadcrumb"},"inLanguage":"da-DK","potentialAction":[{"@type":"ReadAction","target":["https:\/\/dailyai.com\/2023\/10\/machine-learning-reveals-the-contents-of-ancient-scrolls-and-stone-tablets\/"]}]},{"@type":"ImageObject","inLanguage":"da-DK","@id":"https:\/\/dailyai.com\/2023\/10\/machine-learning-reveals-the-contents-of-ancient-scrolls-and-stone-tablets\/#primaryimage","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/shutterstock_308164922.jpg","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/10\/shutterstock_308164922.jpg","width":1000,"height":667},{"@type":"BreadcrumbList","@id":"https:\/\/dailyai.com\/2023\/10\/machine-learning-reveals-the-contents-of-ancient-scrolls-and-stone-tablets\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/dailyai.com\/"},{"@type":"ListItem","position":2,"name":"Machine learning reveals the contents of ancient scrolls and stone tablets"}]},{"@type":"WebSite","@id":"https:\/\/dailyai.com\/#website","url":"https:\/\/dailyai.com\/","name":"DailyAI","description":"Din daglige dosis af AI-nyheder","publisher":{"@id":"https:\/\/dailyai.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/dailyai.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"da-DK"},{"@type":"Organization","@id":"https:\/\/dailyai.com\/#organization","name":"DailyAI","url":"https:\/\/dailyai.com\/","logo":{"@type":"ImageObject","inLanguage":"da-DK","@id":"https:\/\/dailyai.com\/#\/schema\/logo\/image\/","url":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/Daily-Ai_TL_colour.png","contentUrl":"https:\/\/dailyai.com\/wp-content\/uploads\/2023\/06\/Daily-Ai_TL_colour.png","width":4501,"height":934,"caption":"DailyAI"},"image":{"@id":"https:\/\/dailyai.com\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/x.com\/DailyAIOfficial","https:\/\/www.linkedin.com\/company\/dailyaiofficial\/","https:\/\/www.youtube.com\/@DailyAIOfficial"]},{"@type":"Person","@id":"https:\/\/dailyai.com\/#\/schema\/person\/711e81f945549438e8bbc579efdeb3c9","name":"Sam Jeans","image":{"@type":"ImageObject","inLanguage":"da-DK","@id":"https:\/\/secure.gravatar.com\/avatar\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/a24a4a8f8e2a1a275b7491dc9c9f032c401eabf23c3206da4628dc84b6dac5c8?s=96&d=robohash&r=g","caption":"Sam Jeans"},"description":"Sam er videnskabs- og teknologiforfatter og har arbejdet i forskellige AI-startups. N\u00e5r han ikke skriver, kan han finde p\u00e5 at l\u00e6se medicinske tidsskrifter eller grave i kasser med vinylplader.","sameAs":["https:\/\/www.linkedin.com\/in\/sam-jeans-6746b9142\/"],"url":"https:\/\/dailyai.com\/da\/author\/samjeans\/"}]}},"_links":{"self":[{"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/posts\/6435","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/comments?post=6435"}],"version-history":[{"count":6,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/posts\/6435\/revisions"}],"predecessor-version":[{"id":6448,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/posts\/6435\/revisions\/6448"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/media\/6442"}],"wp:attachment":[{"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/media?parent=6435"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/categories?post=6435"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/dailyai.com\/da\/wp-json\/wp\/v2\/tags?post=6435"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}