[물리학의 최전선] Artificial Intelligence, AlphaGo, and Global Optimization

SPEAKER  |  이주영
INSTITUTE  |  고등과학원
DATE  |  April 25(수), 2018
TIME  |  18:00
PLACE  |  대전컨벤션센터
ABSTRACT  |  Many problems in science and engineering can be mapped into combinatorial optimization problems, and examples include protein folding, protein structure prediction/determination, materials design, and community/module detection in the network science. In this talk, I will discuss our recent progresses in solving these problems in terms of the application of the Conformational Space Annealing (CSA) method. I will also discuss the optimization issue in the study of machine learning (ML). A preliminary study indicates that proper application of CSA to ML can provide a solution to the overtraining problem in ML. I will share the progress of our attempt to build our own AlphaGo in this respect.