{"id":133052,"date":"2022-08-24T09:48:08","date_gmt":"2022-08-24T00:48:08","guid":{"rendered":"http:\/\/192.249.19.202\/?post_type=research-achieve&#038;p=133052"},"modified":"2026-04-13T20:09:33","modified_gmt":"2026-04-13T11:09:33","slug":"ee-prof-rhu-minsoos-team-build-first-ever-privacy-aware-a-i-semiconductor-speeding-up-the-differentially-private-learning-process","status":"publish","type":"research-achieve","link":"http:\/\/ee.presscat.kr\/en\/research-achieve\/ee-prof-rhu-minsoos-team-build-first-ever-privacy-aware-a-i-semiconductor-speeding-up-the-differentially-private-learning-process\/","title":{"rendered":"EE Prof. Rhu, Minsoo\u2019s Team Build First-ever Privacy-aware A. I Semiconductor, Speeding Up the Differentially Private Learning Process"},"content":{"rendered":"<blockquote>\n<p><span style=\"font-family: verdana, geneva, sans-serif;font-size: 14pt\"><strong>EE Professor Rhu, Minsoo\u2019s Research Team Build First-ever Privacy-aware Artificial Intelligence Semiconductor, Speeding Up the Differentially Private Learning Process 3.6 Times Google\u2019s TPUv3<\/strong><\/span><\/p>\n<p>&nbsp;<\/p>\n<\/blockquote>\n<p><span style=\"font-family: verdana, geneva, sans-serif\"><img fetchpriority=\"high\" decoding=\"async\" class=\"alignnone size-medium wp-image-133045\" src=\"http:\/\/ee.presscat.kr\/wp-content\/uploads\/2022\/08\/\uc720\ubbfc\uc218\uad50\uc218_\ucea1\ucc98-300x254.jpg\" alt=\"\" width=\"300\" height=\"254\" title=\"\" srcset=\"http:\/\/ee.presscat.kr\/wp-content\/uploads\/2022\/08\/\uc720\ubbfc\uc218\uad50\uc218_\ucea1\ucc98-300x254.jpg 300w, http:\/\/ee.presscat.kr\/wp-content\/uploads\/2022\/08\/\uc720\ubbfc\uc218\uad50\uc218_\ucea1\ucc98.jpg 544w\" sizes=\"(max-width: 300px) 100vw, 300px\" \/><\/span><\/p>\n<p dir=\"ltr\"><span style=\"font-family: verdana, geneva, sans-serif\">[Professor Rhu, Minsoo]<\/span><\/p>\n<p dir=\"ltr\">\u00a0<\/p>\n<p dir=\"ltr\"><span style=\"font-family: verdana, geneva, sans-serif;font-size: 12pt\">EE Professor Rhu and his research team have taken artificial intelligence semiconductors a big leap forward in the application of differentially private machine learning. Professor Rhu\u2019s team analyzed the bottleneck component in the differentially private machine learning performance and devised a semiconductor chip greatly improving differentially private machine learning application performance.<\/span><\/p>\n<p dir=\"ltr\"><span style=\"font-family: verdana, geneva, sans-serif;font-size: 12pt\">Professor Rhu\u2019s artificial intelligence chip consists of, among others, a cross-product-based arithmetic unit and an addition tree-based post-processing arithmetic unit and is capable of 3.6 times faster machine learning process compared with that of Google\u2019s TPUv3, today\u2019s most widely used AI processor. <\/span><\/p>\n<p dir=\"ltr\"><span style=\"font-family: verdana, geneva, sans-serif;font-size: 12pt\">The new chip also boasts comparable performance to that of NVIDIA\u2019s A100 GPU, even with 10 times less resources.<\/span><\/p>\n<p dir=\"ltr\">\u00a0<\/p>\n<p dir=\"ltr\"><span style=\"font-family: verdana, geneva, sans-serif\"><img decoding=\"async\" class=\"alignnone wp-image-133047 \" src=\"http:\/\/ee.presscat.kr\/wp-content\/uploads\/2022\/08\/\uc5f0\uad6c\uc9c44\uba85_\ucea1\ucc98-1024x300.jpg\" alt=\"\" width=\"853\" height=\"250\" title=\"\" srcset=\"http:\/\/ee.presscat.kr\/wp-content\/uploads\/2022\/08\/\uc5f0\uad6c\uc9c44\uba85_\ucea1\ucc98-1024x300.jpg 1024w, http:\/\/ee.presscat.kr\/wp-content\/uploads\/2022\/08\/\uc5f0\uad6c\uc9c44\uba85_\ucea1\ucc98-300x88.jpg 300w, http:\/\/ee.presscat.kr\/wp-content\/uploads\/2022\/08\/\uc5f0\uad6c\uc9c44\uba85_\ucea1\ucc98-768x225.jpg 768w, http:\/\/ee.presscat.kr\/wp-content\/uploads\/2022\/08\/\uc5f0\uad6c\uc9c44\uba85_\ucea1\ucc98.jpg 1111w\" sizes=\"(max-width: 853px) 100vw, 853px\" \/><\/span><\/p>\n<p dir=\"ltr\"><span style=\"font-family: verdana, geneva, sans-serif\">[From left, Co-lead authors Park, Beomsik and Hwang, Ranggi; co-authors Yoon, Dongho and Choi, Yoonhyuk]<\/span><\/p>\n<p dir=\"ltr\">\u00a0<\/p>\n<p dir=\"ltr\"><span style=\"font-family: verdana, geneva, sans-serif\">This work, with EE researchers Park, Beomsik and Hwang, Ranggi as co-first authors, will be presented as\u00a0DiVa: An Accelerator for Differentially Private Machine Learning\u00a0at the 55th IEEE\/ACM International Symposium on Microarchitectures (MICRO 2022), the premier research venue for computer architecture research coming October 1 through 5 in Chicago, USA.<\/span><\/p>\n<p dir=\"ltr\"><span style=\"font-family: verdana, geneva, sans-serif\">Professor Rhu\u2019s achievements have been reported in multiple press coverage.<\/span><\/p>\n<p dir=\"ltr\">\u00a0<\/p>\n<p dir=\"ltr\"><span style=\"font-family: verdana, geneva, sans-serif\">Links:<\/span><\/p>\n<p dir=\"ltr\"><span style=\"font-family: verdana, geneva, sans-serif\">AI Times:\u00a0<a href=\"http:\/\/www.aitimes.com\/news\/articleView.html?idxno=146435\" target=\"_blank\" rel=\"noopener\">http:\/\/www.aitimes.com\/news\/articleView.html?idxno=146435<\/a><\/span><\/p>\n<p dir=\"ltr\"><span style=\"font-family: verdana, geneva, sans-serif\">Yonhap :\u00a0<a href=\"https:\/\/www.yna.co.kr\/view\/AKR20201116072400063?input=1195m\" target=\"_blank\" rel=\"noopener\">https:\/\/www.yna.co.kr\/view\/AKR20201116072400063?input=1195m<\/a><\/span><\/p>\n<p dir=\"ltr\"><span style=\"font-family: verdana, geneva, sans-serif\">Financial News<a href=\"https:\/\/www.fnnews.com\/news\/202208212349474072\" target=\"_blank\" rel=\"noopener\">\u00a0:\u00a0https:\/\/www.fnnews.com\/news\/202208212349474072<\/a><\/span><\/p>\n<p dir=\"ltr\"><span style=\"font-family: verdana, geneva, sans-serif\">Donga Science :\u00a0<a href=\"https:\/\/www.dongascience.com\/news.php?idx=55893\" target=\"_blank\" rel=\"noopener\">https:\/\/www.dongascience.com\/news.php?idx=55893<\/a><\/span><\/p>\n<p dir=\"ltr\"><span style=\"font-family: verdana, geneva, sans-serif\">Industry News :\u00a0<a href=\"http:\/\/www.industrynews.co.kr\/news\/articleView.html?idxno=46829\" target=\"_blank\" rel=\"noopener\">http:\/\/www.industrynews.co.kr\/news\/articleView.html?idxno=46829<\/a><\/span><\/p>\n<div><span style=\"font-family: verdana, geneva, sans-serif\">Boan :\u00a0<a href=\"https:\/\/www.boannews.com\/media\/view.asp?idx=108883&amp;kind=\" target=\"_blank\" rel=\"noopener\">https:\/\/www.boannews.com\/media\/view.asp?idx=108883&amp;kind=<\/a><\/span><\/div>\n<div>\u00a0<\/div>\n","protected":false},"excerpt":{"rendered":"<p>698<\/p>\n","protected":false},"featured_media":133051,"template":"","research_category":[],"class_list":["post-133052","research-achieve","type-research-achieve","status-publish","has-post-thumbnail","hentry"],"acf":[],"_links":{"self":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/research-achieve\/133052","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/research-achieve"}],"about":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/types\/research-achieve"}],"wp:featuredmedia":[{"embeddable":true,"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/media\/133051"}],"wp:attachment":[{"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/media?parent=133052"}],"wp:term":[{"taxonomy":"research_category","embeddable":true,"href":"http:\/\/ee.presscat.kr\/en\/wp-json\/wp\/v2\/research_category?post=133052"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}