Deep learning plays a central role in recent developments in research in artificial intelligence (AI). Various ideas based on physics are found in the research of deep learning, and consequently, deep learning and physics are related intimately. This international conference is dedicated to (1) applications of deep learning to physics, (2) discovering similarities among deep learning and physics, and (3) leading to new paradigm in physics motivated by deep learning. Researchers in related fields are welcome to attending discussions at the conference.
Koji Hashimoto (Osaka U), Masatoshi Imada (Toyota RIKEN / Waseda U), Kouji Kashiwa (Fukuoka Institute of Technology), Yuki Nagai (JAEA), Masayuki Ohzeki (Tohoku U), Enrico Rinaldi (Riken & Arithmer Inc.), Akinori Tanaka (RIKEN AIP), Akio Tomiya (Riken BNL)
31 Oct - 2 Nov 2019
Panasonic Auditorium, Yukawa Hall, Yukawa institute for theoretical physics, Kyoto university
Shun-Ichi Amari (RIKEN)
Hong-Ye Hu (UC San Diego)
Gurtej Kanwar (MIT)
Sven Krippendorf (Arnold Sommerfeld Center)
Junwei Liu (Hong Kong Univ. Sci. Tech.)
Zi Yang Meng (Chinese Academy of Sciences)
Youichiro Miyake (Square Enix)
Masayuki Ohzeki (Tohoku Univ.)
Fabian Ruhle (CERN)
Rak-Kyeong Seong (Samsung SDS)
Gary Shiu (Univ. Wisconsin)
Lei Wang (Chinese Academy of Sciences)
Youhei Yamaji (Tokyo Univ.)
Greg Yang (Microsoft Research)
Hajime Yoshino (Osaka Univ.)
James Halverson (Northeastern Univ.) : Special lecture at Osaka Univ. on 30 October 2019
| First day: Oct 31(Thu) | Second day: Nov 1 (Fri) | Third day: Nov 2 (Sat) |
|---|---|---|
| 9:30-10:20 H.Y. Hu | 9:30-10:20 F. Ruhle | |
| 10:20-11:10 G. Kanwar | 10:20-11:10 J. Liu | |
| Lunch break | Break | |
| 11:40-12:30 Y. Yamaji | ||
| "Physics, AI, Company" session | Lunch break | |
| 13:10 Opening Welcome | 13:00-13:35 R.K. Seong | |
| 13:20-14:10 J. Halverson | 13:35-14:10 Y. Miyake | |
| 14:10-15:00 S. Krippendorf | 14:10-14:45 M. Ohzeki | 14:00-14:50 Z.Y. Meng |
| 15:00-15:50 G. Yang | 14:45-15:00 Discussion | 14:50-15:40 H. Yoshino |
| Break | Break | Break |
| 16:20-17:10 L. Wang | 15:30-18:00 Poster session | 16:10-17:00 G. Shiu |
| 17:10-18:00 S. Amari | 17:00 Closing |
Title and Abstract of invited talks
Slides
J. Halverson: Machine learning & string theory (Lecture in Osaka U.)
J. Halverson: Generative Models and Statistical Predictions in String Theory
S. Krippendorf: Dualities in and from Machine Learning
G. Yang: Tensor Programs: The Feynman Diagrams of Deep Learning
L. Wang: Neural Canonical Transformation
S. Amari: Deep Random Neural Field
G. Kanwar: Flow-based generative models for lattice theories
F. Ruhle: Machine learning for Calabi-Yau metrics
J. Liu: Self-learning Monte Carlo method and all optical neural network
Y. Yamaji: Origin of High-Temperature Superconductivity Revealed by Boltzmann Machine Learning
Z. Y. Meng: What we talk about When we talk about learning in many-body physics
H. Yoshino: From complex to simple : hierarchical free-energy landscape renormalized in deep neral networks
G. Shiu: Decoding the Shape of the String Landscape with Data Science
Deep Learning and physics (Osaka Univ.)
本研究会は新学術領域科研費「次世代物質探索のための離散幾何学」との共催です。
また、 以下の研究費にサポートを受けて開催されます：科研費17H06462、科研費18K13548、 ポスト「京」プロジェクト「世代の産業を支える新機能デバイス・高性能材料の創成」