Course Info

In this seminar course, we will study and develop techniques for accelerating large-scale data analytics using deep learning and other machine-learning techniques. The course will focus on cutting-edge research problems related to video analytics, data exploration, natural language query processing, speech analytics, query optimization, hardware acceleration, and hardware management. By the end of this course, you will be versatile in the state of the art in all of these topics.


  • Format: The course will be a combination of lectures, student presentations, and separate brainstorming sessions in which we will collectively study and develop new ideas related to the covered topics. The students will do projects based on these ideas. The course will provide research opportunities in the areas of data management, machine learning, computer vision, computer architecture, and natural language processing.
  • Prerequisites: Students are expected to have completed an undergraduate-level computer systems course (e.g., database systems, operating systems) and to be comfortable with programming in languages such as Python or C/C++. The course is open to both Ph.D. and M.S. students. Undergraduate students should obtain permission from the instructor.
  • Academic Honesty: Students are expected to abide by the Georgia Tech Honor Code.


This is a seminar course, thus there are no exams. You will be graded on the basis of your participation in projects and presentations. There will be readings assigned for each class. Each class will have one or more presenters whose job it will be to lead the discussion in class about those papers. The non-presenters should prepare a one page review on the assigned paper.

The final grade for the course will be tentatively based on the following weights:

  • 30% — Reading Reviews + Class Participation
  • 20% — Paper Presentations
  • 10% — Project Intermediate Report
  • 30% — Project Final Report
  • 10% — Project Presentation and Poster


This website is based on a design by Andy Pavlo.