Learning with Limited Labeled Data

Offered this year and most years

Fall 2022

As machine learning is deployed more widely, researchers and practitioners keep running into a fundamental problem: how do we get enough labeled data? This seminar course will survey research on learning when only limited labeled data is available. Topics covered include weak supervision, semi-supervised learning, active learning, transfer learning, and few-shot learning. Students will lead discussions on classic and recent research papers, and work in teams on final research projects.

Previous experience in machine learning is required through CSCI1420 or equivalent research experience.

Course Home Page:
Location:CIT 316
Meeting Time:J hr: T, Th 1:00-2:20
Exam Group:08: 21-DEC-2022 Exam Time: 02:00:00 PM