{"blog_url":"https://paper.hatenadiary.jp/","image_url":"https://cdn-ak.f.st-hatena.com/images/fotolife/m/misos/20190127/20190127132139.png","title":" \u8ad6\u6587\u30e1\u30e2\uff1a Dataset Distillation \u306b\u3064\u3044\u3066","provider_name":"Hatena Blog","blog_title":"\u3081\u3082","published":"2019-01-11 00:00:00","type":"rich","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Fpaper.hatenadiary.jp%2Fentry%2F201901050000\" title=\" \u8ad6\u6587\u30e1\u30e2\uff1a Dataset Distillation \u306b\u3064\u3044\u3066 - \u3081\u3082\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","width":"100%","author_url":"https://blog.hatena.ne.jp/misos/","author_name":"misos","height":"190","categories":["\u8ad6\u6587\u3081\u3082","\u6df1\u5c64\u5b66\u7fd2","\u6a5f\u68b0\u5b66\u7fd2"],"provider_url":"https://hatena.blog","version":"1.0","url":"https://paper.hatenadiary.jp/entry/201901050000","description":"\u6982\u8981 \u5143\u8ad6\u6587 \u95a2\u9023\u7814\u7a76 \u30e2\u30c7\u30eb\uff08\u306e\u5b66\u7fd2\u3057\u305f\u77e5\u8b58\uff09\u306e\u84b8\u7559 \u554f\u984c\u8a2d\u5b9a\u30fb\u8a18\u6cd5 \u624b\u6cd5 \u30e2\u30c7\u30eb\u306e\u521d\u671f\u5024\u304c\u56fa\u5b9a\u3055\u308c\u3066\u3044\u308b\u5834\u5408 \u30e2\u30c7\u30eb\u306e\u521d\u671f\u5024\u304c\u30e9\u30f3\u30c0\u30e0\u306b\u6c7a\u5b9a\u3055\u308c\u308b\u5834\u5408 \u5b9f\u9a13\u3067\u6bd4\u8f03\u306b\u7528\u3044\u308b\u3082\u306e \u5b9f\u9a13 \u5b9f\u88c5 \u500b\u4eba\u7528\u306e\u30e1\u30e2\u3002 \u6982\u8981 \u753b\u50cf\u5206\u985e\u30e2\u30c7\u30eb\u306e\u8a13\u7df4\u306b\u3066\u3001\u5b66\u7fd2\u306b\u52b9\u679c\u306e\u9ad8\u3044\u753b\u50cf\u3068\u5b66\u7fd2\u7387\u3092\u5f97\u308b\u624b\u6cd5\u3092\u63d0\u6848 \u30e2\u30c7\u30eb\u306e\u521d\u671f\u30d1\u30e9\u30e1\u30fc\u30bf\u304c\u751f\u6210\u3055\u308c\u308b\u5206\u5e03\u3068\u5b66\u7fd2\u30a8\u30dd\u30c3\u30af\u6570\u306b\u57fa\u3065\u3044\u3066\u753b\u50cf\u3068\u5b66\u7fd2\u7387\u3092\u5f97\u308b CIFAR-10\u306b\u3066100\u306e\u751f\u6210\u753b\u50cf\u304b\u3089Accuracy 50%\u8d8a\u3048 \u73fe\u5b9f\u7684\u306a\u5fdc\u7528\u306e\u4e2d\u3067\u3053\u306e\u624b\u6cd5\u3092\u7528\u3044\u3066\u5f97\u3089\u308c\u305f\u753b\u50cf\u30fb\u5b66\u7fd2\u7387\u304c\u6709\u7528\u306b\u306a\u308b\u30b7\u30c1\u30e5\u30a8\u30fc\u30b7\u30e7\u30f3\u3068\u3057\u3066\u3069\u306e\u3088\u3046\u306a\u3082\u306e\u304c\u3042\u308b\u304b\u306f\u672a\u691c\u8a0e \u5143\u8ad6\u6587 \u30bf\u30a4\u30c8\u30eb: Dataset Di\u2026"}