{"url":"https://tech.jxpress.net/entry/2021/08/26/170000","type":"rich","width":"100%","description":"\u80cc\u666f \u306f\u3058\u3081\u307e\u3057\u3066\u3001JX\u901a\u4fe1\u793e\u3067\u30a4\u30f3\u30bf\u30fc\u30f3\u3092\u3057\u3066\u3044\u308b\u539f\u7530\u3067\u3059\u3002 \u8fd1\u5e74\u6df1\u5c64\u5b66\u7fd2\u3067\u306f\u30e2\u30c7\u30eb\u304c\u80a5\u5927\u5316\u3059\u308b\u50be\u5411\u306b\u3042\u308a\u307e\u3059\u30022020\u5e74\u306bopen ai\u304c\u793a\u3057\u305fScaling Laws\uff08[2001.08361] Scaling Laws for Neural Language Models\uff09 \u306e\u885d\u6483\u306f\u8a18\u61b6\u306b\u65b0\u3057\u304f\u3001MLP-Mixer\u304c\u793a\u3057\u305f\u3088\u3046\u306b\u3001\u30e2\u30c7\u30eb\u3092\u5927\u304d\u304f\u3059\u308c\u3070Attention\u69cb\u9020\u3084CNN\u3067\u3055\u3048\u3082\u4e0d\u5fc5\u8981\u3068\u3044\u3046\u8aac\u3082\u3042\u308a\u307e\u3059\u3002\uff08[2105.01601] MLP-Mixer: An all-MLP Architecture for Vision\uff09 \u3057\u304b\u3057\u5927\u304d\u306a\u6df1\u5c64\u5b66\u7fd2\u30e2\u30c7\u30eb\u3092\u5229\u7528\u3057\u3088\u3046\u3068\u3059\u308b\u3068\u3001\u3057\u3070\u3057\u3070\u2026","blog_title":"JX\u901a\u4fe1\u793e\u30a8\u30f3\u30b8\u30cb\u30a2\u30d6\u30ed\u30b0","categories":["Python","DeepLearning","\u9ad8\u901f\u5316","BERT"],"blog_url":"https://tech.jxpress.net/","image_url":"https://qiita-image-store.s3.ap-northeast-1.amazonaws.com/0/540234/082f697a-637e-d12e-8c24-ded0c089c26f.png","title":"BERT\u306e\u63a8\u8ad6\u901f\u5ea6\u3092\u6700\u592710\u500d\u306b\u3057\u3066\u30c7\u30d7\u30ed\u30a4\u3057\u305f\u8a71\u3068\u305d\u306eTips","author_name":"haraso1130","provider_url":"https://hatena.blog","provider_name":"Hatena Blog","published":"2021-08-26 17:00:00","height":"190","version":"1.0","author_url":"https://blog.hatena.ne.jp/haraso1130/","html":""}