{"id":1577,"date":"2022-03-04T05:30:00","date_gmt":"2022-03-03T20:30:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=1577"},"modified":"2022-03-04T05:30:00","modified_gmt":"2022-03-03T20:30:00","slug":"deepnet-1000%e5%b1%a4%e3%81%aetransformer","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=1577","title":{"rendered":"DeepNet: 1000\u5c64\u306eTransformer"},"content":{"rendered":"\n<ul class=\"wp-block-list\"><li><strong>DeepNet: Scaling Transformers to 1,000 Layers\u00a0<\/strong>[106.3]<br>\u30c8\u30e9\u30f3\u30b9\u30d5\u30a9\u30fc\u30de\u30fc\u306e\u6b8b\u5dee\u63a5\u7d9a\u3092\u4fee\u6b63\u3059\u308b\u305f\u3081\u306e\u65b0\u3057\u3044\u6b63\u898f\u5316\u95a2\u6570(DeepNorm)\u3092\u5c0e\u5165\u3059\u308b\u3002 \u8a73\u7d30\u306a\u7406\u8ad6\u89e3\u6790\u306b\u3088\u308a\u3001\u30e2\u30c7\u30eb\u66f4\u65b0\u306f\u5b89\u5b9a\u306a\u65b9\u6cd5\u3067\u30d0\u30a6\u30f3\u30c9\u3067\u304d\u308b\u3053\u3068\u304c\u793a\u3055\u308c\u3066\u3044\u308b\u3002 \u30c8\u30e9\u30f3\u30b9\u30d5\u30a9\u30fc\u30de\u30fc\u30921,000\u5c64\u307e\u3067\u62e1\u5f35\u3059\u308b\u3053\u3068\u306b\u6210\u529f\u3057\u305f\u304c\u3001\u3053\u308c\u306f\u5f93\u6765\u306e\u30c7\u30a3\u30fc\u30d7\u30c8\u30e9\u30f3\u30b9\u30d5\u30a9\u30fc\u30de\u30fc\u3088\u308a\u30821\u6841\u3082\u6df1\u3044\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2203.00555v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2203.00555v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Tue, 1 Mar 2022 15:36:38 GMT)<ul><li>deepnorm\u3092\u5c0e\u5165\u3059\u308b\u3053\u3068\u3067Transformer\u30921000\u5c64\u307e\u3067\u6df1\u304f\u3067\u304d\u308b\u3068\u306e\u5831\u544a\u3002\u6a5f\u68b0\u7ffb\u8a33\u306b\u304a\u3044\u3066\u6709\u671b\u306a\u7d50\u679c\u3002\u591a\u8a00\u8a9e\u306eM2M-100\u3092\u5927\u304d\u304f\u4e0a\u56de\u308b\u6027\u80fd\u3092\u9054\u6210\u3057\u3066\u3044\u308b\u3088\u3046\u306b\u898b\u3048\u308b\u3002<\/li><li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/microsoft\/unilm\">GitHub &#8211; microsoft\/unilm: Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities<\/a><\/li><\/ul><\/li><\/ul>\n","protected":false},"excerpt":{"rendered":"<p>DeepNet: Scaling Transformers to 1,000 Layers\u00a0[106.3]\u30c8\u30e9\u30f3\u30b9\u30d5\u30a9\u30fc\u30de\u30fc\u306e\u6b8b\u5dee\u63a5\u7d9a\u3092\u4fee\u6b63\u3059\u308b\u305f\u3081\u306e\u65b0\u3057\u3044\u6b63\u898f\u5316\u95a2\u6570(DeepNorm)\u3092\u5c0e\u5165\u3059\u308b\u3002 \u8a73\u7d30\u306a\u7406\u8ad6\u89e3\u6790\u306b\u3088\u308a &hellip; <a href=\"https:\/\/devneko.jp\/wordpress\/?p=1577\" class=\"more-link\"><span class=\"screen-reader-text\">&#8220;DeepNet: 1000\u5c64\u306eTransformer&#8221; \u306e<\/span>\u7d9a\u304d\u3092\u8aad\u3080<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[106,415,505],"class_list":["post-1577","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-deep-learning","tag-transformer","tag-505"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/1577","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=1577"}],"version-history":[{"count":0,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/1577\/revisions"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=1577"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=1577"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=1577"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}