Optimization Methods for Deep Learning


Course Outline

Deep learning involves a difficult non-convex optimization problem. The goal of this course is to study the efficiency and the robustness of optimization methods for deep learning. We will run this course in the following formats: This course is highly research oriented. You want to take it only if you are interested in the research of optimization on deep learning.

Among the various types of networks, we will pay more attention to CNN.


Slides, Reading list, and Projects

This section (and slides) will be continuously updated.

Week 1:
April 1

April 3 Week 2:
April 8 April 10 Week 3:
April 15,17 Week 4:
April 22 April 24 Week 5:
April 29 May 1 Week 6:
May 6 May 8 Week 7:
May 13 May 15 Week 8:
May 20 May 22 Week 9:
May 27 May 29 Week 10:
June 3 June 5 Other possible projects


Exams

No exam

Grading

100% Projects.
Last modified: