|Title||Machine Learning on condensed matter physics|
|Date||2021-08-25~2021-08-26 (Registerable Date : ~ 2021-08-24)|
Hunpyo Lee (Kangwon National University at Samcheok)
Heung-Sik Kim (Kangwon National University)
In-ho Lee (KRISS)
SCOPE OF PROGRAM
Machine learning and data-driven sciences and their applications to various fields of science and engineering, including condensed matter and materials physics, has been intensively studied recently. This TRP program aims to organize an informal-style gathering of condensed matter and materials physics researchers who independently have studied this emerging field of science, and to activate communication and collaboration between domestic and international researchers. Tentative subjects to be addressed are as follows;
*. Data-driven discovery and inverse materials design.
*. Deep-learning applications in physics and materials science:
- Machine-learning-accelerated numerical algorithms.
- High-throughput analyses experimental data using deep-learning models.
- Networks models for physical sciences.
An additional workshop, which will be held in Nov. 2021, will cover broader fields of machine learning application to computational chemical and other physical sciences.
LIST OF SPEAKERS
Prof. Junghyo Jo (SNU)
Prof. Seung-Woo Son (Hanyang Univ.)
Prof. Donghee Kim (GIST)
Prof. Hunpyo Lee (Kangwon National University at Samcheok)
Prof. Sooran Kim (Kyungpook National University)
Dr. Jung-Hoon Lee (KIST)
Dr. Yea-Lee Lee (KRICT)
Dr. Hongkee Yoon (KAIST)
There will be 8 talks including one tutorial-style talk. Tentative time table is as follows;
13:40 to 14:00 - Registration and greetings
14:00 to 15:20 - Session 1 (2 talks including 1 tutorial-style talk, Chair: Hunpyo Lee)
(1) [14:00-14:40] Seung-Woo Son: Reservoir Computing for Study of Chaotic Systems
(2) [14:40-15:20] Junghyo Jo: Machine learning and information theory
16:00 to 18:00 - Session 2 (3 talks on machine learning for strongly correlated electronic systems, Chair: In-ho Lee)
(1) [16:00-16:40] Hunpyo Lee: Self-energy predictions from analytic continuation and ARPES data, via machine learning technique
(2) [16:40-17:20] Sooran Kim: Machine-Learning-Guided Prediction Models of Critical Temperature of Cuprates
(3) [17:20-18:00] Donghee Kim: Two particular applications of a neural network to a phase transition
09:40 to 10:00 - Registration
10:00 to 12:00 - Session 3 (3 talks on machine learning for computational material science, Chair: Heung-Sik Kim)
(1) [10:00-10:40] Hongkee Yoon: Reliably accelerating Monte Carlo simulations with XAI
(2) [10:40-11:20] Jung-Hoon Lee: Inverse Design of Surface Geometries using Al Generative Model
(3) [11:20-12:00] Yea-Lee Lee: Data-Driven Study on Thermoelectric Material Design and Design Principle Extraction Using a Machine Learning Approach
12:00 to 12:10 - Concluding remarks