時間: 2023/6/9(Friday) 4:00PM-5:00PM

講者: Prof. Gitta Kutyniok (Bavarian AI Chair for Mathematical Foundations of Artificial Intelligence; Department of Mathematics, LMU Munich, Germany)

講題: Machine Learning: From Learning Physical Laws to Quantum Computing

 

摘要:

    For most of human history, scientists had to derive physical laws by hand. As the availability of data in physics is growing and machine learning is becoming more powerful, engineers and physicists are aiming to apply machine learning to infer the governing laws from experimental data. The current literature focuses however solely on the development of methods to achieve this goal, and a theoretical foundation is at present missing, which is particularly dangerous, since those algorithms are at present also not reliable.

    In this talk we will first give an introduction into this thriving research field. Then we will discuss our first stage of a theoretical framework, in particular, how to derive well-definedness of the learning problem, both theoretically and numerically. In a second part, we will touch upon fundamental limitations of machine learning, and show that from a computability viewpoint digital hardware causes a serious problem for reliability as well, and reveal a surprising connection to novel computing approaches such as quantum computing.

 

地點: 線上 webex (線上會議連結公告於 NYCU SciML 網頁)

 

NYCU SciML webinar: https://sites.google.com/nycu.edu.tw/nycu-sciml