{"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\/pt\/blog\/news\/intel-rabotaet-nad-opticheskimi-chipami-dlya-bolee-effektivnogo-ii","title":{"rendered":"A Intel est\u00e1 trabalhando em chips \u00f3pticos para uma IA mais eficiente","gt_translate_keys":[{"key":"rendered","format":"text"}]},"content":{"rendered":"

Circuitos fot\u00f4nicos integrados ou chips \u00f3pticos possuem potencialmente v\u00e1rias vantagens em compara\u00e7\u00e3o com seus equivalentes eletr\u00f4nicos, como a redu\u00e7\u00e3o do consumo de energia e a diminui\u00e7\u00e3o da lat\u00eancia em c\u00e1lculos. \u00c9 por isso que muitos pesquisadores acreditam que eles podem ser extremamente eficazes em tarefas de aprendizado de m\u00e1quina e na cria\u00e7\u00e3o de intelig\u00eancia artificial (IA). A Intel tamb\u00e9m v\u00ea grandes perspectivas para a aplica\u00e7\u00e3o da fot\u00f4nica sil\u00edcica nessa dire\u00e7\u00e3o. O grupo de seus pesquisadores em um artigo cient\u00edfico<\/a><\/noindex> detalhou novos m\u00e9todos que podem aproximar as redes neurais \u00f3pticas de se tornarem realidade.<\/p>\n

\"A<\/p>\n

Em uma recente publica\u00e7\u00e3o no blog da Intel<\/a><\/noindex>, dedicado ao aprendizado de m\u00e1quina, conta como come\u00e7aram as pesquisas em redes neurais \u00f3pticas. Os trabalhos cient\u00edficos de David Miller e Michael Reck demonstraram que um tipo de circuito fot\u00f4nico, conhecido como interfer\u00f4metro de Mach-Zehnder (MZI), pode ser configurado para realizar a multiplica\u00e7\u00e3o de matrizes de 2 \u00d7 2, e que, ao posicionar o MZI em uma rede triangular para a multiplica\u00e7\u00e3o de matrizes maiores, \u00e9 poss\u00edvel obter um esquema que implementa o algoritmo de multiplica\u00e7\u00e3o de matriz por vetor \u2014 um c\u00e1lculo fundamental utilizado no aprendizado de m\u00e1quina.<\/p>\n

Um novo estudo da Intel se concentrou em investigar o que acontece ao surgirem diferentes defeitos que afetam os chips \u00f3pticos durante a fabrica\u00e7\u00e3o (uma vez que a fot\u00f4nica computacional \u00e9 an\u00e1loga por natureza), causando diferen\u00e7as na precis\u00e3o dos c\u00e1lculos entre diferentes chips do mesmo tipo. Embora esses tipos de estudos j\u00e1 tenham sido realizados anteriormente, no passado eles foram mais focados na otimiza\u00e7\u00e3o p\u00f3s-fabrica\u00e7\u00e3o para eliminar poss\u00edveis imprecis\u00f5es. No entanto, essa abordagem tem uma escalabilidade limitada, j\u00e1 que as redes est\u00e3o se tornando cada vez maiores, o que leva a um aumento da pot\u00eancia computacional necess\u00e1ria para ajustar as redes \u00f3pticas. Em vez de otimizar ap\u00f3s a fabrica\u00e7\u00e3o, a Intel considerou a possibilidade de um treinamento \u00fanico dos chips antes da produ\u00e7\u00e3o por meio do uso de uma arquitetura resistente a interfer\u00eancias. Uma rede neural \u00f3ptica de refer\u00eancia foi treinada uma vez, ap\u00f3s a qual os par\u00e2metros de aprendizado foram distribu\u00eddos entre v\u00e1rias inst\u00e2ncias fabricadas da rede com diferen\u00e7as em seus componentes.<\/p>\n

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

A equipe da Intel explorou duas arquiteturas para a constru\u00e7\u00e3o de sistemas de intelig\u00eancia artificial baseados em MZI: GridNet e FFTNet. O GridNet posiciona previsivelmente o MZI em uma grade, enquanto o FFTNet os organiza em forma de \"borboletas\". Ap\u00f3s treinar ambas na simula\u00e7\u00e3o de uma tarefa padr\u00e3o de aprendizado profundo de reconhecimento de d\u00edgitos manuscritos (MNIST), os pesquisadores descobriram que o GridNet obteve uma precis\u00e3o mais alta do que o FFTNet (98% contra 95%), mas a arquitetura FFTNet mostrou-se \"significativamente mais confi\u00e1vel\". De fato, o desempenho do GridNet caiu abaixo de 50% com a adi\u00e7\u00e3o de ru\u00eddo artificial (interfer\u00eancias que imitam poss\u00edveis defeitos na fabrica\u00e7\u00e3o de chips \u00f3pticos), enquanto para o FFTNet permaneceu quase constante.<\/p>\n

Cientistas afirmam que suas pesquisas estabelecem as bases para m\u00e9todos de aprendizado de intelig\u00eancia artificial que eliminar\u00e3o a necessidade de ajuste fino dos chips \u00f3pticos ap\u00f3s a produ\u00e7\u00e3o, economizando tempo e recursos preciosos.<\/p>\n

\"Como em qualquer processo de fabrica\u00e7\u00e3o, surgem certos defeitos, o que significa que haver\u00e1 pequenas varia\u00e7\u00f5es entre os chips, e isso impactar\u00e1 a precis\u00e3o dos c\u00e1lculos\", escreve Kazimir Wierzynski, diretor s\u00eanior do grupo de produtos da Intel AI. \"Se as redes neurais \u00f3pticas se tornarem uma parte vi\u00e1vel do ecossistema de hardware da intelig\u00eancia artificial, elas precisar\u00e3o evoluir para chips maiores e tecnologias de produ\u00e7\u00e3o industrial. Nossas pesquisas mostram que a escolha da arquitetura certa antecipadamente pode aumentar significativamente a probabilidade de que os chips obtidos alcancem o desempenho desejado, mesmo com varia\u00e7\u00f5es de fabrica\u00e7\u00e3o.\"<\/p>\n

Ao mesmo tempo, enquanto a Intel est\u00e1 principalmente focada em pesquisa, o candidato a doutorado do MIT, Yichen Shen, fundou a startup Lightelligence, baseada em Boston, que atraiu financiamento de risco no valor de 10,7 milh\u00f5es de d\u00f3lares e recentemente demonstrou<\/a><\/noindex> um prot\u00f3tipo de chip \u00f3ptico para aprendizado de m\u00e1quina que \u00e9 100 vezes mais r\u00e1pido do que os chips eletr\u00f4nicos modernos, al\u00e9m de reduzir significativamente o consumo de energia, o que mais uma vez ilustra as perspectivas das tecnologias fot\u00f4nicas.<\/p>\n

<\/p>\n

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

\t\t\t\t


\n\t\t\t\t\t\t\t\t<\/center>
Fonte: 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\udd47 Intel est\u00e1 desenvolvendo chips \u00f3pticos para um IA mais eficiente | ProHoster","description":"Os circuitos integrados fot\u00f4nicos ou chips \u00f3pticos possuem potencialmente muitas vantagens em rela\u00e7\u00e3o aos seus equivalentes eletr\u00f4nicos, como redu\u00e7\u00e3o do consumo de energia e diminui\u00e7\u00e3o da lat\u00eancia nos c\u00e1lculos.","canonical_url":"https:\/\/prohoster.info\/pt\/blog\/news\/intel-rabotaet-nad-opticheskimi-chipami-dlya-bolee-effektivnogo-ii","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":""},"schema":null,"og:locale":"pt_PT","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\/pt\/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\/pt\/wp-json\/wp\/v2\/posts\/34491","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/comments?post=34491"}],"version-history":[{"count":0,"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/posts\/34491\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/media\/25984"}],"wp:attachment":[{"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/media?parent=34491"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/categories?post=34491"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/prohoster.info\/pt\/wp-json\/wp\/v2\/tags?post=34491"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}