Presentation 2018-08-27
Study on Physics-guided Learning of Deep Neural Network
Junya Tanaka, Tomohiko Tomita, Masayuki Numao, Ken-ichi Fukui,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Machine learning, especially deep learning, have a disadvantage that learning models become complicated and it becomes difficult to understand for the human. Especially in the field of natural sciences exploring the principle, even if high prediction and classification accuracy are obtained, it can not be said that a useful model could be acquired unless the model has descriptivity. In this paper, we develop the useful method with high readability by combining the machine learning model and physical model used in the natural science fields.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Thermal Wind Equation / Physical Model / Neural Network / Geostrophic Wind
Paper # AI2018-14
Date of Issue 2018-08-20 (AI)

Conference Information
Committee AI
Conference Date 2018/8/27(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Tsunenori Mine(Kyushu Univ.)
Vice Chair Daisuke Katagami(Tokyo Polytechnic Univ.) / Naoki Fukuta(Shizuoka Univ.)
Secretary Daisuke Katagami(Ritsumeikan Univ.) / Naoki Fukuta(Univ. of Electro-Comm.)
Assistant Yuko Sakurai(AIST)

Paper Information
Registration To Technical Committee on Artificial Intelligence and Knowledge-Based Processing
Language JPN-ONLY
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Study on Physics-guided Learning of Deep Neural Network
Sub Title (in English)
Keyword(1) Thermal Wind Equation
Keyword(2) Physical Model
Keyword(3) Neural Network
Keyword(4) Geostrophic Wind
1st Author's Name Junya Tanaka
1st Author's Affiliation Osaka University(Osaka Univ)
2nd Author's Name Tomohiko Tomita
2nd Author's Affiliation Kumamoto University(Kumamoto Univ)
3rd Author's Name Masayuki Numao
3rd Author's Affiliation Osaka University(Osaka Univ)
4th Author's Name Ken-ichi Fukui
4th Author's Affiliation Osaka University(Osaka Univ)
Date 2018-08-27
Paper # AI2018-14
Volume (vol) vol.118
Number (no) AI-197
Page pp.pp.7-12(AI),
#Pages 6
Date of Issue 2018-08-20 (AI)