In this class, you will learn about, apply and advance state-of-the-art techniques for learning from visual data with limited human supervision. Much of the tremendous progress in AI and deep learning has focused on supervised learning settings which require people to annotate every piece of training data with a desired system output. This fundamentally limits a system as the vast majority of data available is unsupervised. 

The focus of this course is on reading and critiquing published research papers, and on doing a semester-long research project.

We will read and analyze the strengths and weaknesses of research papers on a variety of important topics pertaining to learning with limited supervision, and identify open research questions. See the schedule for a list of topics we will cover.

Through the course of the semester, you will also undertake a research project with a concrete objective, likely in teams of 3-4 students (depending on enrollment). While certainly not a requirement for the class, students should actively consider submitting a paper at the end of the course to a top-tier conference in Computer Vision, Machine learning, or AI.

Class meets: Tu, Th 2:00-3:15pm 2456 Klaus