DCMB Tools & Technology Seminar: Xiao-Su (Frank) Hu
Medical Science Building1 (MS1), Room 4B700
ZOOMAbout This Event
Join us for the DCMB Tools & Technology Seminar Series featuring a presentation by Xiao-Su (Frank) Hu from MIDAS. Enjoy a complimentary pizza lunch while learning about innovative research and cutting-edge tools.
“AutoGluon: A Practical Guide for Researchers”
Tool Link: https://auto.gluon.ai
MIDAS AI in Research Handbook: https://midas-ai-in-research.readthedocs.io
Abstract
AutoGluon is an open-source AutoML framework that automates model training and selection across multiple data types, including tabular data, text, and images. This talk provides a practical introduction to AutoGluon for researchers who want to incorporate machine learning into their workflows without extensive ML expertise. We will walk through hands-on examples across different data modalities and discuss common pitfalls and best practices for getting reliable results.
Presenters
Xiao-Su (Frank) Hu
Data Scientist
Michigan Institute for Data and AI in Society (MIDAS)
Frank Hu is a Data Scientist at the Michigan Institute for Data and AI in Society (MIDAS). His work focuses on developing and applying machine learning and artificial intelligence methods to complex, high-dimensional data across interdisciplinary domains. He has over 15 years of experience in neuroimaging research, particularly in functional near-infrared spectroscopy (fNIRS) and EEG, and has led projects that integrate multimodal brain signals with advanced computational approaches.
At MIDAS, Frank is expanding his work toward predictive modeling, real-time data analysis, and AI-driven tools that can advance both scientific discovery and practical applications. Beyond neuroimaging, he has broad expertise in statistical modeling, time series analysis, and building end-to-end pipelines for large-scale data, from clinical electronic health records to multimodal sensor data. He is also an active participant in machine learning competitions, which keeps him engaged with cutting-edge methods in applied data science.
Host/Moderator
Marci Brandenburg
Librarian, Library - Health Sciences, University Library