Learning from Imperfect Supervision
Event Date: | April 3, 2025 |
---|---|
Time: | 10:30 AM |
Location: | MSEE 112 |
Priority: | No |
School or Program: | Electrical and Computer Engineering |
College Calendar: | Show |
In person attendance is highly encouraged.
Abstract
In many machine learning applications, collecting a large amount of high-quality labeled data is often challenging. However, relying solely on unlabeled data may not always be reliable. To address this issue, leveraging imperfect data presents a promising approach. In this talk, I will provide an overview of our recent research on developing reliable machine learning methods under imperfect supervision. This includes weakly supervised learning, learning with noisy labels, and transfer learning. Finally, I will discuss how machine learning research should evolve in the era of large foundation models.
Bio
Host
Zoom link: https://purdue-edu.zoom.us/j/99029519791 Meeting ID: 990 2951 9791
2025-04-03 10:30:00 2025-04-03 11:30:00 America/Indiana/Indianapolis Learning from Imperfect Supervision Join Masashi Sugiyama, professor at the University of Tokyo and director of the RIKEN Center for Advanced Intelligence Project, as he speaks on learning from imperfect supervision. MSEE 112 Add to Calendar