Trainees will learn about classical methods in machine learning that are broadly used across scientific domains. The lecture will focus on supervised learning approaches and the concepts needed to successfully use them to solve scientific challenges. Specific topics will include: machine learning algorithms including linear, decision tree, and kernel methods; feature generation and representations for scientific data; and application-aware cross-validation methods.
Day and Time: November 4, 3-5 p.m. US CT
This session is a part of the ALCF AI for Science Training Series.
About the Speaker
Logan is an Assistant Computational Scientist in the Data Science and Learning Division. He currently works as part of the Exascale Computing Project and JCESR on developing machine learning tools for designing new materials on leadership-class supercomputing systems. Logan’s research interests focus on lowering the barriers for other scientists to use AI in their own research through creating new software and methods suited for science. Logan received his PhD in Materials Science and Engineering from Northwestern University in 2017. Previously, he earned Master’s and Bachelor’s Degrees in Materials Science and Engineering from The Ohio State University.