CS 8803 LS Fall 2022
News
August 22: Please check the class schedule to paper readings and schedule of assignments that are due. Enrolled students must sign up to present a paper by Friday Aug 26th. Paper reviews are due twice a week (night before we discuss in class).
August 20: Welcome to CS 8803 - LS! This class meets in person TuTh 2456 Klaus 2:00-3:15pm.
COVID
Class mode: This is a discussion based class. In class participation is highly important for the learning process. However, if you are ill please stay home and contact the instructor in the case of missing a presentation. All slides will be made available online for each class.
Masks in class: The USG will not allow GT to require masks or vaccinations. However, the public health evidence overwhelmingly indicates that both actions are key to reducing transmission and incidence of COVID. I strongly request that you wear a mask to keep yourself and others as safe as we can. I will be wearing a mask at all times.
Subject to change: I will revisit the course mode regularly based on public health information, Georgia Tech rules, and my judgement about the best way to create a good learning experience for this particular class.
Course Information At A Glance
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