{"id":34491,"date":"2019-10-31T21:58:39","date_gmt":"2019-10-31T18:58:39","guid":{"rendered":"https:\/\/prohoster.info\/blog\/intel-rabotaet-nad-opticheskimi-chipami-dlya-bolee-effektivnogo-ii\/"},"modified":"2019-10-31T21:58:39","modified_gmt":"2019-10-31T18:58:39","slug":"intel-rabotaet-nad-opticheskimi-chipami-dlya-bolee-effektivnogo-ii","status":"publish","type":"post","link":"https:\/\/prohoster.info\/hu\/blog\/news\/intel-rabotaet-nad-opticheskimi-chipami-dlya-bolee-effektivnogo-ii","title":{"rendered":"Az Intel optikai chipeken dolgozik a hat\u00e9konyabb mesters\u00e9ges intelligencia \u00e9rdek\u00e9ben.","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

A fotonikus integr\u00e1lt \u00e1ramk\u00f6r\u00f6k vagy optikai chipek potenci\u00e1lisan sz\u00e1mos el\u0151ny\u00fck van az elektronikus megfelel\u0151ikkel szemben, p\u00e9ld\u00e1ul cs\u00f6kkentett energiafogyaszt\u00e1s \u00e9s alacsonyabb k\u00e9sleltet\u00e9s a sz\u00e1m\u00edt\u00e1sok sor\u00e1n. Ez\u00e9rt sok kutat\u00f3 \u00fagy v\u00e9li, hogy rendk\u00edv\u00fcl hat\u00e9konyak lehetnek a g\u00e9pi tanul\u00e1s \u00e9s a mesters\u00e9ges intelligencia (AI) feladataiban. Az Intel c\u00e9g is nagy lehet\u0151s\u00e9geket l\u00e1t a szil\u00edcium-fotonik\u00e1ban ezen a t\u00e9ren. Kutat\u00f3csoportjuk a tudom\u00e1nyos cikkben<\/a><\/noindex> r\u00e9szletesen bemutatta az \u00faj m\u00f3dszereket, amelyek k\u00f6zelebb vihetik az optikai neur\u00e1lis h\u00e1l\u00f3zatokat a val\u00f3s\u00e1ghoz.<\/p>\n

\"Az<\/p>\n

A k\u00f6zelm\u00faltban az Intel blogj\u00e1ban<\/a><\/noindex>, amely a g\u00e9pi tanul\u00e1sra \u00f6sszpontos\u00edt, bemutatja, hogyan kezd\u0151dtek a kutat\u00e1sok az optikai neuronh\u00e1l\u00f3zatok ter\u00e9n. David A. B. Miller \u00e9s Michael Reck tudom\u00e1nyos munk\u00e1i bebizony\u00edtott\u00e1k, hogy az \u00fagynevezett Mach-Zehnder interferom\u00e9ter (MZI) f\u00e9nycs\u00f6ves t\u00edpusa konfigur\u00e1lhat\u00f3 2 \u00d7 2 m\u00e9ret\u0171 m\u00e1trixszoroz\u00e1s elv\u00e9gz\u00e9s\u00e9re. Amennyiben a MZI-t egy h\u00e1romsz\u00f6g r\u00e1csra helyezz\u00fck nagy m\u00e1trixok szorz\u00e1s\u00e1hoz, egy olyan s\u00e9m\u00e1t kaphatunk, amely a m\u00e1trixvektor szorz\u00e1s algoritmus\u00e1t val\u00f3s\u00edtja meg \u2013 ez az alapvet\u0151 sz\u00e1m\u00edt\u00e1s, amely a g\u00e9pi tanul\u00e1sban haszn\u00e1latos.<\/p>\n

Az Intel \u00faj kutat\u00e1sa arra \u00f6sszpontos\u00edt, hogy mi t\u00f6rt\u00e9nik, amikor k\u00fcl\u00f6nb\u00f6z\u0151 hib\u00e1k l\u00e9pnek fel az optikai chipek gy\u00e1rt\u00e1sa sor\u00e1n (mivel a sz\u00e1m\u00edt\u00e1stechnikai fotonika term\u00e9szet\u00e9n\u00e9l fogva anal\u00f3g), amelyek elt\u00e9r\u00e9seket okoznak a k\u00fcl\u00f6nb\u00f6z\u0151 t\u00edpus\u00fa chipek sz\u00e1m\u00edt\u00e1si pontoss\u00e1g\u00e1ban. B\u00e1r hasonl\u00f3 kutat\u00e1sokat m\u00e1r v\u00e9geztek, ezek a m\u00faltban ink\u00e1bb a gy\u00e1rt\u00e1s ut\u00e1ni optimaliz\u00e1l\u00e1sra \u00f6sszpontos\u00edtottak a lehets\u00e9ges pontatlans\u00e1gok megsz\u00fcntet\u00e9se \u00e9rdek\u00e9ben. Ennek a megk\u00f6zel\u00edt\u00e9snek azonban gyenge a sk\u00e1l\u00e1zhat\u00f3s\u00e1ga, mivel a h\u00e1l\u00f3zatok egyre nagyobb\u00e1 v\u00e1lnak, ami a sz\u00fcks\u00e9ges sz\u00e1m\u00edt\u00e1si kapacit\u00e1s n\u00f6veked\u00e9s\u00e9hez vezet az optikai h\u00e1l\u00f3zatok finomhangol\u00e1s\u00e1hoz. Az Intel a gy\u00e1rt\u00e1s ut\u00e1ni optimaliz\u00e1l\u00e1s helyett a chipek egyszeri betan\u00edt\u00e1s\u00e1nak lehet\u0151s\u00e9g\u00e9t m\u00e9rlegelte, a zavarokkal szemben ellen\u00e1ll\u00f3 architekt\u00fara alkalmaz\u00e1s\u00e1val. Egy referencia optikai neur\u00e1lis h\u00e1l\u00f3zatot egyszer tan\u00edtottak be, majd a tanulm\u00e1nyi param\u00e9tereket t\u00f6bb legy\u00e1rtott h\u00e1l\u00f3zati p\u00e9ld\u00e1nyra osztott\u00e1k el, k\u00fcl\u00f6nb\u00f6z\u0151 komponensekkel.<\/p>\n

<\/center><\/p>\n

Az Intel csapata k\u00e9t architekt\u00far\u00e1t vizsg\u00e1lt az MZI alap\u00fa mesters\u00e9ges intelligencia rendszerek fel\u00e9p\u00edt\u00e9s\u00e9re: a GridNet-et \u00e9s az FFTNet-et. A GridNet el\u0151rel\u00e1that\u00f3an a MZI-t egy r\u00e1csba helyezi, m\u00edg az FFTNet \u201epillang\u00f3kk\u00e9nt\u201d helyezi el \u0151ket. A k\u00e9t architekt\u00fara tanulm\u00e1nyoz\u00e1sa ut\u00e1n a k\u00e9z\u00edr\u00e1sos sz\u00e1mok (MNIST) m\u00e9lytanul\u00e1si referenciafeladat\u00e1n a kutat\u00f3k felfedezt\u00e9k, hogy a GridNet magasabb pontoss\u00e1got \u00e9rt el, mint az FFTNet (98 % szemben 95 %-kal), azonban az FFTNet architekt\u00fara \u201ejelent\u0151sen megb\u00edzhat\u00f3bbnak\u201d bizonyult. Val\u00f3j\u00e1ban a GridNet teljes\u00edtm\u00e9nye 50 % al\u00e1 esett, amikor mesters\u00e9ges zajt adtak hozz\u00e1 (olyan zavar\u00f3 t\u00e9nyez\u0151ket, amelyek a f\u00e9nychip gy\u00e1rt\u00e1s\u00e1nak esetleges hib\u00e1it ut\u00e1nozz\u00e1k), m\u00edg az FFTNet teljes\u00edtm\u00e9nye szinte \u00e1lland\u00f3 maradt.<\/p>\n

A tud\u00f3sok azt \u00e1ll\u00edtj\u00e1k, hogy kutat\u00e1saik alapot adnak a mesters\u00e9ges intelligencia tanul\u00e1si m\u00f3dszereihez, amelyek seg\u00edtenek megsz\u00fcntetni az optikai chipek gy\u00e1rt\u00e1s ut\u00e1ni finomhangol\u00e1s\u00e1nak sz\u00fcks\u00e9gess\u00e9g\u00e9t, ezzel \u00e9rt\u00e9kes id\u0151t \u00e9s er\u0151forr\u00e1sokat megtakar\u00edtva.<\/p>\n

\u201eAhogy b\u00e1rmely gy\u00e1rt\u00e1si folyamatban, itt is felmer\u00fclnek bizonyos hib\u00e1k, amelyek azt jelentik, hogy a mikroszk\u00e9m\u00e1k k\u00f6z\u00f6tt kisebb elt\u00e9r\u00e9sek lesznek, \u00e9s ezek hat\u00e1ssal lesznek a sz\u00e1m\u00edt\u00e1sok pontoss\u00e1g\u00e1ra\u201d \u2013 \u00edrja Kazimir Wierzynski, az Intel AI term\u00e9kcsoportj\u00e1nak vezet\u0151 igazgat\u00f3ja. \u201eHa az optikai neuronh\u00e1l\u00f3k \u00e9letk\u00e9pes r\u00e9sz\u00e9v\u00e9 v\u00e1lnak a mesters\u00e9ges intelligencia hardverek \u00f6kosziszt\u00e9m\u00e1j\u00e1nak, nagyobb mikroszk\u00e9m\u00e1kra \u00e9s ipari gy\u00e1rt\u00e1si technol\u00f3gi\u00e1kra lesz sz\u00fcks\u00e9g\u00fck. Kutat\u00e1saink azt mutatj\u00e1k, hogy a megfelel\u0151 architekt\u00fara el\u0151zetes kiv\u00e1laszt\u00e1sa jelent\u0151sen n\u00f6velheti annak val\u00f3sz\u00edn\u0171s\u00e9g\u00e9t, hogy a gy\u00e1rtott mikroszk\u00e9m\u00e1k el\u00e9rj\u00e9k a k\u00edv\u00e1nt teljes\u00edtm\u00e9nyt m\u00e9g a gy\u00e1rt\u00e1si vari\u00e1ci\u00f3k ellen\u00e9re is.\u201d<\/p>\n

Ek\u00f6zben, m\u00edg az Intel f\u0151k\u00e9nt kutat\u00e1sokat folytat, a Massachusetts Institute of Technology fizikatudom\u00e1nyi doktori hallgat\u00f3ja, Yichen Shen l\u00e9trehozta a bostoni sz\u00e9khely\u0171 Lightelligence startupot, amely 10,7 milli\u00f3 doll\u00e1ros kock\u00e1zati t\u0151k\u00e9t vonzott, \u00e9s r\u00f6vid id\u0151n bel\u00fcl bemutatta<\/a><\/noindex> a mesters\u00e9ges intelligenci\u00e1ra sz\u00e1nt optikai chip protot\u00edpus\u00e1t, amely 100-szor gyorsabb a jelenlegi elektronikus chipekn\u00e9l \u00e9s nagys\u00e1grenddel cs\u00f6kkenti az energiafogyaszt\u00e1st, ami \u00fajra vil\u00e1gosan bemutatja a fotonikus technol\u00f3gi\u00e1k lehet\u0151s\u00e9geit.<\/p>\n

<\/p>\n

<\/center><\/p>\n

\t\t\t\t


\n\t\t\t\t\t\t\t\t<\/center>
Forr\u00e1s: 3dnews.ru<\/a><\/p>","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"excerpt":{"rendered":"

\u0424\u043e\u0442\u043e\u043d\u043d\u044b\u0435 \u0438\u043d\u0442\u0435\u0433\u0440\u0430\u043b\u044c\u043d\u044b\u0435 \u0441\u0445\u0435\u043c\u044b \u0438\u043b\u0438 \u043e\u043f\u0442\u0438\u0447\u0435\u0441\u043a\u0438\u0435 \u0447\u0438\u043f\u044b \u043f\u043e\u0442\u0435\u043d\u0446\u0438\u0430\u043b\u044c\u043d\u043e \u043e\u0431\u043b\u0430\u0434\u0430\u044e\u0442 \u043c\u043d\u043e\u0436\u0435\u0441\u0442\u0432\u043e\u043c \u043f\u0440\u0435\u0438\u043c\u0443\u0449\u0435\u0441\u0442\u0432 \u043f\u043e \u0441\u0440\u0430\u0432\u043d\u0435\u043d\u0438\u044e \u0441 \u044d\u043b\u0435\u043a\u0442\u0440\u043e\u043d\u043d\u044b\u043c\u0438 \u0430\u043d\u0430\u043b\u043e\u0433\u0430\u043c\u0438, \u0442\u0430\u043a\u0438\u043c\u0438 \u043a\u0430\u043a \u0441\u043d\u0438\u0436\u0435\u043d\u0438\u0435 \u044d\u043d\u0435\u0440\u0433\u043e\u043f\u043e\u0442\u0440\u0435\u0431\u043b\u0435\u043d\u0438\u044f \u0438 \u0443\u043c\u0435\u043d\u044c\u0448\u0435\u043d\u0438\u0435 \u0437\u0430\u0434\u0435\u0440\u0436\u043a\u0438 \u0432 \u0432\u044b\u0447\u0438\u0441\u043b\u0435\u043d\u0438\u044f\u0445. \u0412\u043e\u0442 \u043f\u043e\u0447\u0435\u043c\u0443 \u043c\u043d\u043e\u0436\u0435\u0441\u0442\u0432\u043e \u0438\u0441\u0441\u043b\u0435\u0434\u043e\u0432\u0430\u0442\u0435\u043b\u0435\u0439 \u0441\u0447\u0438\u0442\u0430\u044e\u0442, \u0447\u0442\u043e \u043e\u043d\u0438 \u043c\u043e\u0433\u0443\u0442 \u043e\u043a\u0430\u0437\u0430\u0442\u044c\u0441\u044f \u043a\u0440\u0430\u0439\u043d\u0435 \u044d\u0444\u0444\u0435\u043a\u0442\u0438\u0432\u043d\u044b \u0432 \u0437\u0430\u0434\u0430\u0447\u0430\u0445 \u043c\u0430\u0448\u0438\u043d\u043d\u043e\u0433\u043e \u043e\u0431\u0443\u0447\u0435\u043d\u0438\u044f \u0438 \u0441\u043e\u0437\u0434\u0430\u043d\u0438\u044f \u0438\u0441\u043a\u0443\u0441\u0441\u0442\u0432\u0435\u043d\u043d\u043e\u0433\u043e \u0438\u043d\u0442\u0435\u043b\u043b\u0435\u043a\u0442\u0430 (\u0418\u0418). \u041a\u043e\u043c\u043f\u0430\u043d\u0438\u044f Intel \u0442\u0430\u043a\u0436\u0435 \u0432\u0438\u0434\u0438\u0442 \u0431\u043e\u043b\u044c\u0448\u0438\u0435 \u043f\u0435\u0440\u0441\u043f\u0435\u043a\u0442\u0438\u0432\u044b \u0434\u043b\u044f \u043f\u0440\u0438\u043c\u0435\u043d\u0435\u043d\u0438\u044f \u043a\u0440\u0435\u043c\u043d\u0438\u0435\u0432\u043e\u0439 \u0444\u043e\u0442\u043e\u043d\u0438\u043a\u0438 \u0432 […]<\/p>\n","protected":false,"gt_translate_keys":[{"key":"rendered","format":"html"}]},"author":1,"featured_media":25984,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[702],"tags":[],"class_list":["post-34491","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\udd47Az Intel optikai chipeken dolgozik a hat\u00e9konyabb AI \u00e9rdek\u00e9ben | ProHoster","description":"A fotonikus integr\u00e1lt \u00e1ramk\u00f6r\u00f6k vagy optikai chippek potenci\u00e1lisan sz\u00e1mos el\u0151nnyel rendelkeznek az elektronikus anal\u00f3gokkal szemben, p\u00e9ld\u00e1ul az energiafogyaszt\u00e1s cs\u00f6kkent\u00e9se \u00e9s a sz\u00e1m\u00edt\u00e1si k\u00e9sleltet\u00e9s minimaliz\u00e1l\u00e1sa.","canonical_url":"https:\/\/prohoster.info\/hu\/blog\/news\/intel-rabotaet-nad-opticheskimi-chipami-dlya-bolee-effektivnogo-ii","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\udd47Intel \u0440\u0430\u0431\u043e\u0442\u0430\u0435\u0442 \u043d\u0430\u0434 \u043e\u043f\u0442\u0438\u0447\u0435\u0441\u043a\u0438\u043c\u0438 \u0447\u0438\u043f\u0430\u043c\u0438 \u0434\u043b\u044f \u0431\u043e\u043b\u0435\u0435 \u044d\u0444\u0444\u0435\u043a\u0442\u0438\u0432\u043d\u043e\u0433\u043e \u0418\u0418 | ProHoster","og:description":"\u0424\u043e\u0442\u043e\u043d\u043d\u044b\u0435 \u0438\u043d\u0442\u0435\u0433\u0440\u0430\u043b\u044c\u043d\u044b\u0435 \u0441\u0445\u0435\u043c\u044b \u0438\u043b\u0438 \u043e\u043f\u0442\u0438\u0447\u0435\u0441\u043a\u0438\u0435 \u0447\u0438\u043f\u044b \u043f\u043e\u0442\u0435\u043d\u0446\u0438\u0430\u043b\u044c\u043d\u043e \u043e\u0431\u043b\u0430\u0434\u0430\u044e\u0442 \u043c\u043d\u043e\u0436\u0435\u0441\u0442\u0432\u043e\u043c \u043f\u0440\u0435\u0438\u043c\u0443\u0449\u0435\u0441\u0442\u0432 \u043f\u043e \u0441\u0440\u0430\u0432\u043d\u0435\u043d\u0438\u044e \u0441 \u044d\u043b\u0435\u043a\u0442\u0440\u043e\u043d\u043d\u044b\u043c\u0438 \u0430\u043d\u0430\u043b\u043e\u0433\u0430\u043c\u0438, \u0442\u0430\u043a\u0438\u043c\u0438 \u043a\u0430\u043a \u0441\u043d\u0438\u0436\u0435\u043d\u0438\u0435 \u044d\u043d\u0435\u0440\u0433\u043e\u043f\u043e\u0442\u0440\u0435\u0431\u043b\u0435\u043d\u0438\u044f \u0438 \u0443\u043c\u0435\u043d\u044c\u0448\u0435\u043d\u0438\u0435 \u0437\u0430\u0434\u0435\u0440\u0436\u043a\u0438 \u0432 \u0432\u044b\u0447\u0438\u0441\u043b\u0435\u043d\u0438\u044f\u0445.","og:url":"https:\/\/prohoster.info\/hu\/blog\/news\/intel-rabotaet-nad-opticheskimi-chipami-dlya-bolee-effektivnogo-ii","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":"2019-10-31T18:58:39+00:00","article:modified_time":"2019-10-31T18:58:39+00:00","article:publisher":"https:\/\/www.facebook.com\/prohoster","article:author":"https:\/\/www.facebook.com\/prohoster"},"aioseo_meta_data":{"post_id":"34491","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":"2026-01-21 19:28:19","breadcrumb_settings":null,"limit_modified_date":false,"reviewed_by":null,"ai":null,"created":"2021-03-01 02:20:55","updated":"2026-01-21 19:28:19","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\/34491","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=34491"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/posts\/34491\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/media\/25984"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/media?parent=34491"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/categories?post=34491"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/hu\/wp-json\/wp\/v2\/tags?post=34491"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}