AI is touching every discipline and our daily lives. However, our current AI systems need to learn from massive amounts of data to be effective, and they can easily make surprisingly wrong, misleading decisions. In this talk, I'll describe my group's research in building the foundations and tools to enable AI systems to make reliable predictions, even if only limited data are available, and safeguard them against costly mistakes, leading to breakthroughs in AI's scientific, engineering, and medical applications.
Ju Sun is an assistant professor at the Department of Computer Science & Engineering, the University of Minnesota at Twin Cities (UMN). His research interests span computer vision, machine learning, numerical optimization, data science, computational imaging, and healthcare. His recent efforts are focused on the foundation and computation for deep learning and applying deep learning to tackle challenging science, engineering, and medical problems. Before this, he worked as a postdoc scholar at Stanford University (2016-2019), and obtained his Ph.D. degree from Columbia University's Electrical Engineering in 2016. He won the best student paper award from SPARS'15, honorable mention of doctoral thesis for the New World Mathematics Awards (NWMA) 2017, and AAAI New Faculty Highlight Programs 2021, Frontiers of Science Award in Mathematics 2024, and the McKnight Land-Grant Professorship of UMN 2025-2027.