{"title":"HiPPO/S4\u89e3\u8aac","provider_name":"Hatena Blog","version":"1.0","type":"rich","width":"100%","description":"\u3053\u3093\u306b\u3061\u306f\u3001CTO\u5ba4\u30ea\u30b5\u30fc\u30c1\u30e3\u30fc\u306e\u89d2\u7530\u3067\u3059\u3002 \u793e\u5185\u3067\u306f\u6bce\u9031\u91d1\u66dc\u65e5\u306b\u6301\u3061\u56de\u308a\u3067\u8ad6\u6587\u7d39\u4ecb\u3092\u884c\u3046journal club\u3068\u3044\u3046\u6d3b\u52d5\u3092\u884c\u3063\u3066\u304a\u308a\u307e\u3059\u3002\u305d\u3061\u3089\u3067\u79c1\u304c\u767a\u8868\u3057\u305f\u4ee5\u4e0b\uff13\u672c\u306e\u8ad6\u6587 HiPPO: Recurrent Memory with Optimal Polynomial Projections (NeurIPS 2020 Spotlight) Combining Recurrent, Convolutional, and Continuous-time Models with the Linear State Space Layer (NeurIPS 2021) Efficiently Mo\u2026","author_name":"morphotech","blog_title":"Morpho Tech Blog","categories":["\u6587\u732e\u7d39\u4ecb"],"height":"190","blog_url":"https://techblog.morphoinc.com/","html":"<iframe src=\"https://hatenablog-parts.com/embed?url=https%3A%2F%2Ftechblog.morphoinc.com%2Fentry%2F2022%2F05%2F24%2F102648\" title=\"HiPPO/S4\u89e3\u8aac - Morpho Tech Blog\" class=\"embed-card embed-blogcard\" scrolling=\"no\" frameborder=\"0\" style=\"display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;\"></iframe>","provider_url":"https://hatena.blog","url":"https://techblog.morphoinc.com/entry/2022/05/24/102648","author_url":"https://blog.hatena.ne.jp/morphotech/","published":"2022-05-24 10:26:48","image_url":null}