Neurons to Numerical Analysis: Applications of machine learning in scientific computing

Zoom link for remote participants

TEACHING FACULTY CANDIDATE

Abstract:

One of the most common tasks in machine learning is regression, or the ability to predict the output of a system given an input. In this lecture, we will begin with an overview of the basic theory behind linear regression. We will then apply this theoretical background to solve a simple linear regression problem. After that, we will consider how the same principles that we learned in linear regression can be applied to solving regression problems for more complex functions. To conclude, we will examine how regression in machine learning can be used to solve real world multiphysics problems in a research context.

Bio:

Kevin Wandke received his B.S. in Mechanical Science and Engineering in 2019, and his M.S. in Electrical Engineering in 2022, both from the University of Illinois at Urbana-Champaign. He is currently pursuing his Ph.D. in Electrical and Computer Engineering at University of Illinois at Urbana-Champaign. He previously worked at Argonne National laboratory as a member of the SULI program, and at General Electric’s Global research center as an intern in the Edison Engineering Program. Additionally, he is the recipient of the Chancellor’s Scholarship, Olsen award for Excellence in Undergraduate Teaching, and a Mavis Future Faculty Fellow in the Grainger College of Engineering.

Kevin’s research focuses on two major themes, computational modeling, and pedagogy. Within the theme of computational modeling, he has focused on ways to use machine learning to accelerate the modeling of complex multiphysics processes. Within the area of pedagogy, Kevin has focused on ways to provide adaptive instruction to large courses, as well as ways to deliver content through various modalities to improve the learning experiences of students.