{"id":3473,"date":"2024-06-14T10:48:09","date_gmt":"2024-06-14T01:48:09","guid":{"rendered":"http:\/\/cinetjp-static3.nict.go.jp\/english\/?post_type=event&p=3473"},"modified":"2024-10-28T15:45:56","modified_gmt":"2024-10-28T06:45:56","slug":"20240726_8766","status":"publish","type":"event","link":"http:\/\/cinetjp-static3.nict.go.jp\/english\/event\/20240726_8766\/","title":{"rendered":"Friday Lunch Seminar: Takashi Matsubara: “Make Deep Learning Model Faithful to Physics” (On-line for CiNet members only: Sign-up required)"},"content":{"rendered":"\n

Friday Lunch Seminar (English)
July 26, 2024 (JST)\u3000\u3000
12:15 \u301c 13:00
On-line<\/p>\n\n\n\n

Talk Title\uff1aMake Deep Learning Model Faithful to Physics<\/p>\n\n\n\n

Takashi Matsubara
Professor
Faculty of Information Science and Technology
Hokkaido University<\/p>\n\n\n\n

Host PI : Naoki Wakamiya<\/a><\/p>\n\n\n\n

Abstract:
System identification is the process of discovering the underlying dynamical systems from observed data and can be considered a type of machine learning. However, identifying the correct equations is not straightforward. Recent developments in deep learning have inspired extensive methods that uncover stability and laws of physics from observed data, instead of equations, ensuring that learned dynamical systems adhere to these properties. This talk will introduce deep learning methods designed for dynamical systems, with the primary focus on the presenter’s recent research.<\/p>\n\n\n\n

<\/p>\n","protected":false},"featured_media":0,"template":"","acf":[],"_links":{"self":[{"href":"http:\/\/cinetjp-static3.nict.go.jp\/english\/wp-json\/wp\/v2\/event\/3473"}],"collection":[{"href":"http:\/\/cinetjp-static3.nict.go.jp\/english\/wp-json\/wp\/v2\/event"}],"about":[{"href":"http:\/\/cinetjp-static3.nict.go.jp\/english\/wp-json\/wp\/v2\/types\/event"}],"wp:attachment":[{"href":"http:\/\/cinetjp-static3.nict.go.jp\/english\/wp-json\/wp\/v2\/media?parent=3473"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}