Course Schedule
Weekday Regular Schedule
Group | Type | Hours | Location |
---|---|---|---|
All | Lecture | Sunday 13:00-16:00 | Orenstein 103 |
Detailed Schedule
Lecture | Date | Topics | Slides | Scribes |
---|---|---|---|---|
1 | 19/3 | Introduction to the course. Kernel regression classifiers. Graphical Model intro | Lecture | Kernel Regression, Graphical Models Representation |
2 | 26/3 | Exact Inference in Graphical Models | Lecture | |
3 | 2/4 | Reinforcement Learning | Lecture | |
4 | 23/4 | Approximate inference in Graphical Models | Exact Inference and Approximate Inference | |
5 | 30/4 | Approximate inference in Graphical Models | Sampling Methods | |
6 | 7/5 | Parameter Estimation and Structured Prediction | Slides on Structured Prediction | Parameter Learning Pseudo Likelihood |
7 | 14/5 | Overview of deep learning (focus on supervised) | Slides | |
8 | 21/5 | Unsupervised Deep Learning | Slides | |
9 | 28/5 | Reinforcement Learning | Policy Gradient Methods | Policy Search Review , Sutton & Barto Book, Pieter Abbeel Tutorial, David Silver Tutorial |
10 | 4/6 | Reinforcement Learning | Value Based Methods | |
11 | 11/6 | Generalization Bounds | Rademacher Complexity | |
12 | 16/6 | Generalization Bounds | ||
13 | 25/6 | Project Presentation |
Code for kernel regression: solver, RBF kernel