1. 일시 : 05월 09일 (금) 오후 4시-5시
2. 장소 : 아산이학관 526호(권택연 세미나실)
3. 연사 : 최민석 교수님 (포스텍 수학과)
4. 제목 : Scientific Machine Learning: Algorithms and Applications
5. 초록 : Scientific Machine Learning (SML) is rapidly emerging as a powerful approach for tackling complex problems in science and engineering by integrating machine learning with real-world data and the fundamental laws of physics. This talk will provide a concise overview of core SML concepts and key algorithms. We will introduce methodologies such as Physics-Informed Neural Networks (PINNs), which embed physical constraints directly into the learning process, and Operator Learning, which learn the behavior of an entire system in function spaces, thereby enabling fast and efficient prediction of the system’s response to various input conditions. Furthermore, we will discuss recent advancements in SML designed to overcome challenges associated with the original PINNs and operator learning. Finally, we will explore concrete examples of how SML is being applied to achieve innovative results, often with a significant speed-up compared to traditional numerical simulations.