초 청 세 미 나

Machine learning in optical simulation, from scratch

---------------------------------------------------------------------------------------------------------------

▶ 연사 : 이동열 대표 (블루세미콜론)
▶ 일시 : 2023년 06월 19, 21, 23일(월, 수, 금) (월, 금: 10:00~12:00, 수: 15:30~17:30)
▶ 장소 : 월, 금: 301동 920호, 수: 301동 1020호

---------------------------------------------------------------------------------------------------------------
■ Abstract
Deep learning has emerged as a powerful tool with diverse applications spanning multiple fields,
including physics, chemistry, and optics. This seminar offers participants an opportunity to delve
into the foundational concepts of mathematics and computer science that form the basis of deep
learning, enabling them to develop a comprehensive understanding of its application in solving
optical problems. The seminar is structured into three distinct parts. In the first part, participants
will explore statistical analysis, information theory, and convex optimization. The second part delves
into artificial neural networks and computer engineering concepts. Lastly, the third part focuses on
optical studies that leverage deep learning techniques, such as Physics Informed Neural Networks
and inverse design. The objective of this seminar is to demystify the complexities of machine
learning and provide newly entering engineers with a strong foundation to effectively apply these
concepts in the field of optics.

■ Biography
He is currently a founder at Bluesemicolon, a startup. He received his B.S. and M.S. degrees in
electrical and computer engineering from Seoul National University in 2014 and 2016, respectively.
He is interested in optical simulation and computer science, particularly their applications in
industry.

■ Contact : 정윤찬 교수 (yoonchan@snu.ac.kr)