Time & Place. Tuesdays/Thursdays 11:00-12:15.
Instructor. Parisa Kordjamshidi (Office hours: Stanley Thomas 305 B, Tu/Th 3:30-5:00pm).
This course is a graduate level Machine Learning course. However, it is open to a small number of undergraduate students too.
We will cover a number of introductory topics and classic machine learning approaches as well as several advanced techniques. The advanced topics that are covered in this course include structured output prediction techniques based on generalized linear models, Constrained Conditional Models, Learning, and inference with Probabilistic Graphical Models, Learning with deep architectures in addition to learning techniques for semi-supervised learning.
Since this course covers advanced research topics, I will not follow a single reference. Most of the material is spread in tutorials and papers. However, see the list of some references below.
Recommended General Books