Az IBM bemutatta a CodeNet kezdem\u00e9nyez\u00e9st, amelynek c\u00e9lja, hogy a kutat\u00f3k sz\u00e1m\u00e1ra egy adatgy\u0171jtem\u00e9nyt biztos\u00edtson, lehet\u0151v\u00e9 t\u00e9ve, hogy g\u00e9pi tanul\u00e1si m\u00f3dszerekkel k\u00eds\u00e9rletezzenek programoz\u00e1si nyelvek k\u00f6z\u00f6tti ford\u00edt\u00f3k, valamint k\u00f3dgener\u00e1torok \u00e9s k\u00f3danaliz\u00e1torok l\u00e9trehoz\u00e1s\u00e1val. A CodeNet 14 milli\u00f3 k\u00f3dmint\u00e1t tartalmaz, amelyek 4053 tipikus programoz\u00e1si probl\u00e9m\u00e1t oldanak meg. A gy\u0171jtem\u00e9ny \u00f6sszesen k\u00f6r\u00fclbel\u00fcl 500 milli\u00f3 k\u00f3dsort foglal mag\u00e1ba, \u00e9s 55 programoz\u00e1si nyelvet \u00f6lel fel, bele\u00e9rtve a modern nyelveket, mint a C++, Java, Python \u00e9s Go, valamint az elavultakat, mint a COBOL, Pascal \u00e9s FORTRAN. A projekt eredm\u00e9nyeit Apache 2.0 licenc alatt terjesztik, a adatgy\u0171jtem\u00e9nyek pedig ny\u00edlt k\u00f6zkinccs\u00e9 t\u00e9telre tervezettek. <\/p>\n
A p\u00e9ld\u00e1k annot\u00e1ci\u00f3kkal vannak ell\u00e1tva, \u00e9s azonos algoritmusokat val\u00f3s\u00edtanak meg k\u00fcl\u00f6nb\u00f6z\u0151 programoz\u00e1si nyelveken. Felt\u00e9telezhet\u0151, hogy az aj\u00e1nlott k\u00e9szlet seg\u00edteni fog a g\u00e9pi tanul\u00e1si rendszerek k\u00e9pz\u00e9s\u00e9ben \u00e9s az innov\u00e1ci\u00f3k fejleszt\u00e9s\u00e9ben a ford\u00edt\u00e1s \u00e9s a g\u00e9pi k\u00f3delemz\u00e9s ter\u00fclet\u00e9n, hasonl\u00f3an ahhoz, ahogyan az annot\u00e1lt k\u00e9pek adatb\u00e1zisa, az ImageNet seg\u00edtette a k\u00e9pfelismer\u0151 rendszerek \u00e9s a g\u00e9pi l\u00e1t\u00e1s fejl\u0151d\u00e9s\u00e9t. A gy\u0171jtem\u00e9ny egyik f\u0151 forr\u00e1sa k\u00fcl\u00f6nb\u00f6z\u0151 programoz\u00e1si versenyek eml\u00edt\u00e9se. <\/p>\n
A hagyom\u00e1nyos, szab\u00e1lyalap\u00fa ford\u00edt\u00f3khoz k\u00e9pest a g\u00e9pi tanul\u00e1si rendszerek k\u00e9pesek meg\u00e9rteni \u00e9s figyelembe venni a k\u00f3d haszn\u00e1lat\u00e1nak kontextus\u00e1t. Egy programoz\u00e1si nyelvr\u0151l a m\u00e1sikra val\u00f3 ford\u00edt\u00e1skor a kontextus \u00e9ppolyan fontos, mint egy emberi nyelvr\u0151l a m\u00e1sikra val\u00f3 ford\u00edt\u00e1skor. \u00c9ppen a kontextus figyelembev\u00e9tel\u00e9nek hi\u00e1nya akad\u00e1lyozza a k\u00f3dok \u00e1talak\u00edt\u00e1s\u00e1t elavult nyelvekr\u0151l, mint p\u00e9ld\u00e1ul a COBOL. <\/p>\n
A k\u00fcl\u00f6nb\u00f6z\u0151 nyelveken megval\u00f3s\u00edtott algoritmusok nagy adatb\u00e1zisa seg\u00edti az univerz\u00e1lis g\u00e9pi tanul\u00e1si rendszerek l\u00e9trehoz\u00e1s\u00e1t, amelyek a konkr\u00e9t nyelvek k\u00f6z\u00f6tti k\u00f6zvetlen ford\u00edt\u00e1s helyett egy, a programoz\u00e1si nyelvekt\u0151l f\u00fcggetlen, absztrakt k\u00f3d\u00e1br\u00e1zol\u00e1ssal dolgoznak. Ilyen rendszer haszn\u00e1lhat\u00f3 ford\u00edt\u00f3k\u00e9nt, amely a megadott k\u00f3dot b\u00e1rmely t\u00e1mogatott nyelvre ford\u00edtja az adott bels\u0151 absztrakt k\u00f3dk\u00e9pviselet\u00e9be, ahonnan k\u00e9s\u0151bb k\u00f3d gener\u00e1lhat\u00f3 sz\u00e1mos nyelven. <\/p>\n
A rendszer k\u00e9pes lesz bidirekcion\u00e1lis \u00e1talak\u00edt\u00e1sokra. P\u00e9ld\u00e1ul a bankokban \u00e9s \u00e1llami int\u00e9zm\u00e9nyekben tov\u00e1bbra is haszn\u00e1lj\u00e1k a r\u00e9gi COBOL programoz\u00e1si nyelvet. A g\u00e9pi tanul\u00e1son alapul\u00f3 ford\u00edt\u00f3 k\u00e9pes \u00e1tkonvert\u00e1lni a COBOL k\u00f3dot Java program lesz\u00e1rmazott\u00e1, \u00e9s sz\u00fcks\u00e9g eset\u00e9n a Java t\u00f6red\u00e9ket vissza is ford\u00edtani COBOL k\u00f3dra. <\/p>\n
A nyelvek k\u00f6z\u00f6tti ford\u00edt\u00e1s mellett a CodeNet alkalmaz\u00e1si ter\u00fcletei k\u00f6z\u00e9 tartozik a k\u00f3d keres\u0151 intelligens rendszerek l\u00e9trehoz\u00e1sa \u00e9s a kl\u00f3nok automatikus \u00e9szlel\u00e9se, valamint optimaliz\u00e1l\u00f3 \u00e9s automatikus k\u00f3djav\u00edt\u00f3 rendszerek fejleszt\u00e9se. K\u00fcl\u00f6n\u00f6sen a CodeNet bemutatott p\u00e9ld\u00e1i metaadatokkal vannak ell\u00e1tva, amelyek le\u00edrj\u00e1k a teljes\u00edtm\u00e9nytesztel\u00e9s eredm\u00e9nyeit, a program v\u00e9gs\u0151 m\u00e9ret\u00e9t, a mem\u00f3riafogyaszt\u00e1st \u00e9s azt az \u00e1llapotot, amely lehet\u0151v\u00e9 teszi a helyes \u00e9s hib\u00e1s k\u00f3d megk\u00fcl\u00f6nb\u00f6ztet\u00e9s\u00e9t (a helyes k\u00f3d \u00e9s a hib\u00e1s k\u00f3d megk\u00fcl\u00f6nb\u00f6ztet\u00e9s\u00e9hez a gy\u0171jtem\u00e9nybe sz\u00e1nd\u00e9kosan hib\u00e1s p\u00e9ld\u00e1kat is belefoglalnak, amelyek ar\u00e1nya 29,5%). A g\u00e9pi tanul\u00e1si rendszer figyelembe veheti ezeket a metaadatokat a legoptim\u00e1lisabb k\u00f3d gener\u00e1l\u00e1s\u00e1hoz vagy regresszi\u00f3k \u00e9szlel\u00e9s\u00e9hez az elemzett k\u00f3dban (a rendszer k\u00e9pes meg\u00e9rteni, ha a megadott k\u00f3dban az algoritmus nem optim\u00e1lisan van v\u00e9grehajtva, vagy hib\u00e1kat tartalmaz). \u041a\u043e\u043c\u043f\u0430\u043d\u0438\u044f IBM \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u043b\u0430 \u0438\u043d\u0438\u0446\u0438\u0430\u0442\u0438\u0432\u0443 CodeNet, \u043d\u0430\u0446\u0435\u043b\u0435\u043d\u043d\u0443\u044e \u043d\u0430 \u043f\u0440\u0435\u0434\u043e\u0441\u0442\u0430\u0432\u043b\u0435\u043d\u0438\u0435 \u0438\u0441\u0441\u043b\u0435\u0434\u043e\u0432\u0430\u0442\u0435\u043b\u044f\u043c \u043d\u0430\u0431\u043e\u0440\u0430 \u0434\u0430\u043d\u043d\u044b\u0445, \u043f\u043e\u0437\u0432\u043e\u043b\u044f\u044e\u0449\u0438\u0445 \u044d\u043a\u0441\u043f\u0435\u0440\u0438\u043c\u0435\u043d\u0442\u0438\u0440\u043e\u0432\u0430\u0442\u044c \u0441 \u043f\u0440\u0438\u043c\u0435\u043d\u0435\u043d\u0438\u0435\u043c \u043c\u0435\u0442\u043e\u0434\u043e\u0432 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u0434\u043b\u044f \u0441\u043e\u0437\u0434\u0430\u043d\u0438\u044f \u0442\u0440\u0430\u043d\u0441\u043b\u044f\u0442\u043e\u0440\u043e\u0432 \u0438\u0437 \u043e\u0434\u043d\u043e\u0433\u043e \u044f\u0437\u044b\u043a\u0430 \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u044f \u0432 \u0434\u0440\u0443\u0433\u043e\u0439, \u0430 \u0442\u0430\u043a\u0436\u0435 \u0433\u0435\u043d\u0435\u0440\u0430\u0442\u043e\u0440\u043e\u0432 \u0438 \u0430\u043d\u0430\u043b\u0438\u0437\u0430\u0442\u043e\u0440\u043e\u0432 \u043a\u043e\u0434\u0430. CodeNet \u0432\u043a\u043b\u044e\u0447\u0430\u0435\u0442 \u043a\u043e\u043b\u043b\u0435\u043a\u0446\u0438\u044e \u0438\u0437 14 \u043c\u0438\u043b\u043b\u0438\u043e\u043d\u043e\u0432 \u043f\u0440\u0438\u043c\u0435\u0440\u043e\u0432 \u043a\u043e\u0434\u0430, \u0440\u0435\u0448\u0430\u044e\u0449\u0438\u0445 4053 \u0442\u0438\u043f\u043e\u0432\u044b\u0445 \u043f\u0440\u043e\u0431\u043b\u0435\u043c \u043f\u0440\u043e\u0433\u0440\u0430\u043c\u043c\u0438\u0440\u043e\u0432\u0430\u043d\u0438\u044f. \u0412 \u0441\u0443\u043c\u043c\u0435 \u043a\u043e\u043b\u043b\u0435\u043a\u0446\u0438\u044f \u043d\u0430\u0441\u0447\u0438\u0442\u044b\u0432\u0430\u0435\u0442 \u043e\u043a\u043e\u043b\u043e 500 \u043c\u043b\u043d \u0441\u0442\u0440\u043e\u043a \u043a\u043e\u0434\u0430 […]<\/p>\n","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[702],"tags":[],"class_list":["post-100141","post","type-post","status-publish","format-standard","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\udd47 Az IBM megnyitotta a CodeNet-et a g\u00e9pi tanul\u00e1si rendszerek sz\u00e1m\u00e1ra, amelyek ford\u00edtj\u00e1k \u00e9s ellen\u0151rzik a k\u00f3dot | ProHoster","description":"Az IBM bemutatta a CodeNet kezdem\u00e9nyez\u00e9st, amely a kutat\u00f3k sz\u00e1m\u00e1ra adat\u00e1llom\u00e1nyokat biztos\u00edt, hogy k\u00eds\u00e9rletezzenek a g\u00e9pi tanul\u00e1s m\u00f3dszereinek alkalmaz\u00e1s\u00e1val a ford\u00edt\u00f3k l\u00e9trehoz\u00e1s\u00e1hoz.","canonical_url":"https:\/\/prohoster.info\/hu\/blog\/news\/ibm-otkryl-codenet-dlya-sistem-mashinnogo-obucheniya-transliruyushhih-i-proveryayushhih-kod","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\udd47IBM \u043e\u0442\u043a\u0440\u044b\u043b CodeNet \u0434\u043b\u044f \u0441\u0438\u0441\u0442\u0435\u043c \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f, \u0442\u0440\u0430\u043d\u0441\u043b\u0438\u0440\u0443\u044e\u0449\u0438\u0445 \u0438 \u043f\u0440\u043e\u0432\u0435\u0440\u044f\u044e\u0449\u0438\u0445 \u043a\u043e\u0434 | ProHoster","og:description":"\u041a\u043e\u043c\u043f\u0430\u043d\u0438\u044f IBM \u043f\u0440\u0435\u0434\u0441\u0442\u0430\u0432\u0438\u043b\u0430 \u0438\u043d\u0438\u0446\u0438\u0430\u0442\u0438\u0432\u0443 CodeNet, \u043d\u0430\u0446\u0435\u043b\u0435\u043d\u043d\u0443\u044e \u043d\u0430 \u043f\u0440\u0435\u0434\u043e\u0441\u0442\u0430\u0432\u043b\u0435\u043d\u0438\u0435 \u0438\u0441\u0441\u043b\u0435\u0434\u043e\u0432\u0430\u0442\u0435\u043b\u044f\u043c \u043d\u0430\u0431\u043e\u0440\u0430 \u0434\u0430\u043d\u043d\u044b\u0445, \u043f\u043e\u0437\u0432\u043e\u043b\u044f\u044e\u0449\u0438\u0445 \u044d\u043a\u0441\u043f\u0435\u0440\u0438\u043c\u0435\u043d\u0442\u0438\u0440\u043e\u0432\u0430\u0442\u044c \u0441 \u043f\u0440\u0438\u043c\u0435\u043d\u0435\u043d\u0438\u0435\u043c \u043c\u0435\u0442\u043e\u0434\u043e\u0432 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u0434\u043b\u044f \u0441\u043e\u0437\u0434\u0430\u043d\u0438\u044f \u0442\u0440\u0430\u043d\u0441\u043b\u044f\u0442\u043e\u0440\u043e\u0432 \u0438\u0437 \u043e\u0434\u043d\u043e\u0433\u043e.","og:url":"https:\/\/prohoster.info\/hu\/blog\/news\/ibm-otkryl-codenet-dlya-sistem-mashinnogo-obucheniya-transliruyushhih-i-proveryayushhih-kod","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":"2021-05-11T20:22:44+00:00","article:modified_time":"2021-05-11T20:22:44+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":{"post_id":"100141","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":null,"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":"2021-05-11 22:29:58","updated":"2022-09-28 07:50:50","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\/100141","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=100141"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/posts\/100141\/revisions"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/media?parent=100141"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/categories?post=100141"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/tags?post=100141"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
\n
Forr\u00e1s: opennet.ru<\/a> <\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"