{"id":103181,"date":"2022-02-03T09:36:41","date_gmt":"2022-02-03T07:36:42","guid":{"rendered":"https:\/\/prohoster.info\/blog\/novosti-interneta\/deepmind-predstavil-sistemu-mashinnogo-obucheniya-dlya-generaczii-koda-po-tekstovomu-opisaniyu-zadachi"},"modified":"2022-02-03T09:36:41","modified_gmt":"2022-02-03T07:36:42","slug":"deepmind-predstavil-sistemu-mashinnogo-obucheniya-dlya-generaczii-koda-po-tekstovomu-opisaniyu-zadachi","status":"publish","type":"post","link":"https:\/\/prohoster.info\/hu\/blog\/news\/deepmind-predstavil-sistemu-mashinnogo-obucheniya-dlya-generaczii-koda-po-tekstovomu-opisaniyu-zadachi","title":{"rendered":"A DeepMind bemutatott egy g\u00e9pi tanul\u00e1son alapul\u00f3 rendszert, amely k\u00f3dot gener\u00e1l sz\u00f6veges feladatle\u00edr\u00e1s alapj\u00e1n.","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

A DeepMind, amely a mesters\u00e9ges intelligencia \u00e9s az emberi szint\u0171 sz\u00e1m\u00edt\u00f3g\u00e9pes \u00e9s t\u00e1rsasj\u00e1t\u00e9kokban val\u00f3 r\u00e9szv\u00e9telre k\u00e9pes neur\u00e1lis h\u00e1l\u00f3zatok fejleszt\u00e9s\u00e9vel v\u00e1lt ismertt\u00e9, bemutatta az AlphaCode projektet, amely egy g\u00e9pi tanul\u00e1si rendszert fejleszt a k\u00f3dgener\u00e1l\u00e1shoz. Ez a rendszer k\u00e9pes r\u00e9szt venni a Codeforces programoz\u00f3i versenyein, \u00e9s \u00e1tlagos teljes\u00edtm\u00e9nyt mutat. A fejleszt\u00e9s kulcsfontoss\u00e1g\u00fa jellemz\u0151je, hogy k\u00f3dot tud gener\u00e1lni Python vagy C++ nyelveken, angol nyelv\u0171 feladatmegfogalmaz\u00e1s alapj\u00e1n. <\/p>\n

A rendszer tesztel\u00e9s\u00e9hez 10 \u00faj Codeforces versenyt v\u00e1lasztottak ki, amelyekben t\u00f6bb mint 5000 r\u00e9sztvev\u0151 indult, \u00e9s amelyek a g\u00e9pi tanul\u00e1si modell tr\u00e9ningje ut\u00e1n zajlottak. Az AlphaCode feladatainak elv\u00e9gz\u00e9s\u00e9nek eredm\u00e9nyei alapj\u00e1n a rendszer k\u00f6r\u00fclbel\u00fcl a versenyteljes\u00edtm\u00e9nyek k\u00f6z\u00e9pmez\u0151ny\u00e9ben helyezkedett el (54,3%-os teljes\u00edtm\u00e9nnyel). Az AlphaCode v\u00e1rhat\u00f3 \u00f6sszes\u00edtett pontsz\u00e1ma 1238 pont, ami a Codeforces \u00f6sszes r\u00e9sztvev\u0151j\u00e9nek legjobb 28%-\u00e1ba val\u00f3 beker\u00fcl\u00e9st jelenti, akik az elm\u00falt 6 h\u00f3napban legal\u00e1bb egyszer r\u00e9szt vettek versenyeken. Megjegyzik, hogy a projekt m\u00e9g kezdeti fejleszt\u00e9si szakaszban van, \u00e9s a j\u00f6v\u0151ben tervezik a gener\u00e1lt k\u00f3d min\u0151s\u00e9g\u00e9nek jav\u00edt\u00e1s\u00e1t, valamint az AlphaCode olyan rendszerekk\u00e9 t\u00f6rt\u00e9n\u0151 fejleszt\u00e9s\u00e9t, amelyek seg\u00edtik a k\u00f3d\u00edr\u00e1st vagy alkalmaz\u00e1sfejleszt\u0151 eszk\u00f6z\u00f6kk\u00e9 v\u00e1lnak, amelyeket programoz\u00e1si ismeretek n\u00e9lk\u00fcl is haszn\u00e1lhatnak az emberek. <\/p>\n

A projekt a \u201eTransformer\u201d neur\u00e1lis h\u00e1l\u00f3zat architekt\u00far\u00e1j\u00e1t haszn\u00e1lja, kombin\u00e1lva mintav\u00e9telez\u00e9si \u00e9s sz\u0171r\u00e9si m\u00f3dszerekkel, amelyek lehet\u0151v\u00e9 teszik, hogy k\u00fcl\u00f6nb\u00f6z\u0151, kisz\u00e1m\u00edthatatlan k\u00f3dvari\u00e1nsokat gener\u00e1ljanak, amelyek megfelelnek a term\u00e9szetes nyelv\u0171 sz\u00f6vegnek. A sz\u0171r\u00e9s, klaszterez\u00e9s \u00e9s rangsorol\u00e1s ut\u00e1n a kialakul\u00f3 v\u00e1ltozatok \u00e1raml\u00e1s\u00e1b\u00f3l a legoptim\u00e1lisabb m\u0171k\u00f6d\u0151 k\u00f3dot v\u00e1lasztj\u00e1k ki, amelyet ezut\u00e1n ellen\u0151riznek a helyes eredm\u00e9ny el\u00e9r\u00e9s\u00e9nek \u00e9rdek\u00e9ben (minden versenyfeladatn\u00e1l meg van adva egy bel\u00e9p\u0151 adat p\u00e9lda \u00e9s a hozz\u00e1 tartoz\u00f3 eredm\u00e9ny, amelyet a program v\u00e9grehajt\u00e1sa ut\u00e1n kell kapni).

\"A<\/center> <\/p>\n

A g\u00e9pi tanul\u00e1si rendszer durva edz\u00e9s\u00e9hez az GitHub nyilv\u00e1nos repozit\u00f3riumaiban el\u00e9rhet\u0151 k\u00f3dalap volt haszn\u00e1lva. A kezdeti modell el\u0151k\u00e9sz\u00edt\u00e9se ut\u00e1n az optimaliz\u00e1l\u00e1si f\u00e1zis val\u00f3sult meg, amely egy k\u00f3dgy\u0171jtem\u00e9nyt alapul v\u00e9ve k\u00e9sz\u00fclt, amelyben a Codeforces, CodeChef, HackerEarth, AtCoder \u00e9s Aizu versenyeinek feladatmegold\u00e1si p\u00e9ld\u00e1it tal\u00e1lhat\u00f3k. \u00d6sszesen 715 GB GitHub k\u00f3dot \u00e9s t\u00f6bb mint egymilli\u00f3 tipikus versenyp\u00e9ldafeladat megold\u00e1s\u00e1t haszn\u00e1lt\u00e1k az edz\u00e9s sor\u00e1n. A k\u00f3dgener\u00e1l\u00e1s el\u0151tt a feladat sz\u00f6vege egy normaliz\u00e1l\u00f3 f\u00e1zison ment kereszt\u00fcl, amely sor\u00e1n minden felesleges r\u00e9szletet elt\u00e1vol\u00edtottak, \u00edgy csak a jelent\u0151s r\u00e9szek maradtak meg.

\"A<\/center>
\n
Forr\u00e1s: opennet.ru<\/a> <\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"

\u041a\u043e\u043c\u043f\u0430\u043d\u0438\u044f DeepMind, \u043f\u043e\u043b\u0443\u0447\u0438\u0432\u0448\u0430\u044f \u0438\u0437\u0432\u0435\u0441\u0442\u043d\u043e\u0441\u0442\u044c \u0441\u0432\u043e\u0438\u043c\u0438 \u0440\u0430\u0437\u0440\u0430\u0431\u043e\u0442\u043a\u0430\u043c\u0438 \u0432 \u043e\u0431\u043b\u0430\u0441\u0442\u0438 \u0438\u0441\u043a\u0443\u0441\u0441\u0442\u0432\u0435\u043d\u043d\u043e\u0433\u043e \u0438\u043d\u0442\u0435\u043b\u043b\u0435\u043a\u0442\u0430 \u0438 \u043f\u043e\u0441\u0442\u0440\u043e\u0435\u043d\u0438\u044f \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u044b\u0445 \u0441\u0435\u0442\u0435\u0439, \u0441\u043f\u043e\u0441\u043e\u0431\u043d\u044b\u0445 \u0438\u0433\u0440\u0430\u0442\u044c \u0432 \u043a\u043e\u043c\u043f\u044c\u044e\u0442\u0435\u0440\u043d\u044b\u0435 \u0438 \u043d\u0430\u0441\u0442\u043e\u043b\u044c\u043d\u044b\u0435 \u0438\u0433\u0440\u044b \u043d\u0430 \u0443\u0440\u043e\u0432\u043d\u0435 \u0447\u0435\u043b\u043e\u0432\u0435\u043a\u0430, \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u043b\u0430 \u043f\u0440\u043e\u0435\u043a\u0442 Alpha\u0421ode, \u0440\u0430\u0437\u0432\u0438\u0432\u0430\u044e\u0449\u0438\u0439 \u0441\u0438\u0441\u0442\u0435\u043c\u0443 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u0434\u043b\u044f \u0433\u0435\u043d\u0435\u0440\u0430\u0446\u0438\u0438 \u043a\u043e\u0434\u0430, \u0441\u043f\u043e\u0441\u043e\u0431\u043d\u0443\u044e \u0443\u0447\u0430\u0441\u0442\u0432\u043e\u0432\u0430\u0442\u044c \u0432 \u0441\u043e\u0440\u0435\u0432\u043d\u043e\u0432\u0430\u043d\u0438\u044f\u0445 \u043f\u043e \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u044e \u043d\u0430 \u043f\u043b\u0430\u0442\u0444\u043e\u0440\u043c\u0435 Codeforces \u0438 \u0434\u0435\u043c\u043e\u043d\u0441\u0442\u0440\u0438\u0440\u043e\u0432\u0430\u0442\u044c \u0441\u0440\u0435\u0434\u043d\u0438\u0439 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442. \u041a\u043b\u044e\u0447\u0435\u0432\u043e\u0439 \u043e\u0441\u043e\u0431\u0435\u043d\u043d\u043e\u0441\u0442\u044c\u044e \u0440\u0430\u0437\u0440\u0430\u0431\u043e\u0442\u043a\u0438 \u044f\u0432\u043b\u044f\u0435\u0442\u0441\u044f \u044f\u0432\u043b\u044f\u0435\u0442\u0441\u044f \u0441\u043f\u043e\u0441\u043e\u0431\u043d\u043e\u0441\u0442\u044c \u0433\u0435\u043d\u0435\u0440\u0438\u0440\u043e\u0432\u0430\u0442\u044c \u043a\u043e\u0434 […]<\/p>\n","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"author":1,"featured_media":103182,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[702],"tags":[],"class_list":["post-103181","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news"],"aioseo_notices":[],"aioseo_head":"\n\t\t\n\t\n\t\n\t\n\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\t\t\n\n","aioseo_head_json":{"title":"\ud83e\udd47A DeepMind bemutatta a g\u00e9pi tanul\u00e1si rendszert, amely k\u00e9pes k\u00f3dot gener\u00e1lni a feladat sz\u00f6veges le\u00edr\u00e1sa alapj\u00e1n | ProHoster","description":"A DeepMind, amely h\u00edress\u00e9 v\u00e1lt az AI \u00e9s a sz\u00e1m\u00edt\u00f3g\u00e9pes \u00e9s t\u00e1rsasj\u00e1t\u00e9kokra emberi szint\u0171 teljes\u00edtm\u00e9nyt ny\u00fajt\u00f3 neur\u00e1lis h\u00e1l\u00f3zatok fejleszt\u00e9s\u00e9nek ter\u00e9n, bemutatta projektj\u00e9t.","canonical_url":"https:\/\/prohoster.info\/hu\/blog\/news\/deepmind-predstavil-sistemu-mashinnogo-obucheniya-dlya-generaczii-koda-po-tekstovomu-opisaniyu-zadachi","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"hu_HU","og:site_name":"ProHoster | \u041a\u0443\u043f\u0438\u0442\u044c \u043d\u0430\u0434\u0435\u0436\u043d\u044b\u0439 \u0445\u043e\u0441\u0442\u0438\u043d\u0433 \u0434\u043b\u044f \u0441\u0430\u0439\u0442\u043e\u0432 \u0441 \u0437\u0430\u0449\u0438\u0442\u043e\u0439 \u043e\u0442 DDoS, VPS VDS \u0441\u0435\u0440\u0432\u0435\u0440\u044b","og:type":"article","og:title":"\ud83e\udd47DeepMind \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u043b \u0441\u0438\u0441\u0442\u0435\u043c\u0443 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u0434\u043b\u044f \u0433\u0435\u043d\u0435\u0440\u0430\u0446\u0438\u0438 \u043a\u043e\u0434\u0430 \u043f\u043e \u0442\u0435\u043a\u0441\u0442\u043e\u0432\u043e\u043c\u0443 \u043e\u043f\u0438\u0441\u0430\u043d\u0438\u044e \u0437\u0430\u0434\u0430\u0447\u0438 | ProHoster","og:description":"\u041a\u043e\u043c\u043f\u0430\u043d\u0438\u044f DeepMind, \u043f\u043e\u043b\u0443\u0447\u0438\u0432\u0448\u0430\u044f \u0438\u0437\u0432\u0435\u0441\u0442\u043d\u043e\u0441\u0442\u044c \u0441\u0432\u043e\u0438\u043c\u0438 \u0440\u0430\u0437\u0440\u0430\u0431\u043e\u0442\u043a\u0430\u043c\u0438 \u0432 \u043e\u0431\u043b\u0430\u0441\u0442\u0438 \u0438\u0441\u043a\u0443\u0441\u0441\u0442\u0432\u0435\u043d\u043d\u043e\u0433\u043e \u0438\u043d\u0442\u0435\u043b\u043b\u0435\u043a\u0442\u0430 \u0438 \u043f\u043e\u0441\u0442\u0440\u043e\u0435\u043d\u0438\u044f \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u044b\u0445 \u0441\u0435\u0442\u0435\u0439, \u0441\u043f\u043e\u0441\u043e\u0431\u043d\u044b\u0445 \u0438\u0433\u0440\u0430\u0442\u044c \u0432 \u043a\u043e\u043c\u043f\u044c\u044e\u0442\u0435\u0440\u043d\u044b\u0435 \u0438 \u043d\u0430\u0441\u0442\u043e\u043b\u044c\u043d\u044b\u0435 \u0438\u0433\u0440\u044b \u043d\u0430 \u0443\u0440\u043e\u0432\u043d\u0435 \u0447\u0435\u043b\u043e\u0432\u0435\u043a\u0430, \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u043b\u0430 \u043f\u0440\u043e\u0435\u043a\u0442.","og:url":"https:\/\/prohoster.info\/hu\/blog\/news\/deepmind-predstavil-sistemu-mashinnogo-obucheniya-dlya-generaczii-koda-po-tekstovomu-opisaniyu-zadachi","og:image":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:secure_url":"https:\/\/prohoster.info\/wp-content\/uploads\/2021\/11\/logo-350.jpg","og:image:width":350,"og:image:height":350,"article:published_time":"2022-02-03T07:36:42+00:00","article:modified_time":"2022-02-03T07:36:42+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":{"post_id":"103181","title":null,"description":null,"keywords":null,"keyphrases":null,"primary_term":null,"canonical_url":null,"og_title":null,"og_description":null,"og_object_type":"default","og_image_type":"default","og_image_url":null,"og_image_width":null,"og_image_height":null,"og_image_custom_url":null,"og_image_custom_fields":null,"og_video":null,"og_custom_url":null,"og_article_section":null,"og_article_tags":null,"twitter_use_og":false,"twitter_card":"default","twitter_image_type":"default","twitter_image_url":null,"twitter_image_custom_url":null,"twitter_image_custom_fields":null,"twitter_title":null,"twitter_description":null,"schema":{"blockGraphs":[],"customGraphs":[],"default":{"data":{"Article":[],"Course":[],"Dataset":[],"FAQPage":[],"Movie":[],"Person":[],"Product":[],"ProductReview":[],"Car":[],"Recipe":[],"Service":[],"SoftwareApplication":[],"WebPage":[]},"graphName":"","isEnabled":true},"graphs":[]},"schema_type":"default","schema_type_options":null,"pillar_content":false,"robots_default":true,"robots_noindex":false,"robots_noarchive":false,"robots_nosnippet":false,"robots_nofollow":false,"robots_noimageindex":false,"robots_noodp":false,"robots_notranslate":false,"robots_max_snippet":null,"robots_max_videopreview":null,"robots_max_imagepreview":"large","priority":null,"frequency":null,"local_seo":null,"seo_analyzer_scan_date":null,"breadcrumb_settings":null,"limit_modified_date":false,"reviewed_by":null,"ai":null,"created":"2022-02-03 07:37:52","updated":"2022-09-28 18:00:26","focus_keyword":null,"additional_keywords":null,"truseo_locale":null},"gt_translate_keys":[{"key":"link","format":"url"}],"_links":{"self":[{"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/posts\/103181","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/comments?post=103181"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/posts\/103181\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/media\/103182"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/media?parent=103181"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/categories?post=103181"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/tags?post=103181"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}