The following is a preliminary schedule of the lectures and presentations for CS 4033/5033 Machine Learning for Fall 2010. This specific order of each topic will depend on the class projects and interest. This will be finalized in the first week. The schedule will be updated throughout the semester as we delve deeper into special topics and/or add additional topics of interest. The project deadlines are in red and will not change, even if other parts of the schedule change. Major new topics are noted in blue.
| Date | Topic | Assigned Reading | Assigned | Due |
| Aug 24 (Week 1) | What is machine learning? What will I learn if I take this class? Types of machine learning. | |||
| Aug 26 Reinforcement Learning | Introduction to RL, Project introduction | Chapter 1 (Sutton & Barto) | Project | Pretest |
| Aug 31 (Week 2) | Oral project proposals |
|||
| Sep 2 | Intro to RL, Exploration & Exploitation | 2.1-2.3, 2.5-2.7 (Sutton & Barto) | ||
| Sep 7 (Week 3) | The RL problem | Chapter 3 (Sutton & Barto) |
HW 1 | Written proposal |
| Sep 9 | The RL problem | |||
| Sep 14 (Week 4) | The RL problem | HW 2 | HW 1 | |
| Sep 16 | Dynamic Programming | Chapter 4 (Sutton & Barto) | ||
| Sep 21 (Week 5) | Temporal Difference learning | 6.1-6.5, 6.8 (Sutton & Barto) |
Checkpoint 1 | |
| Sep 23 | Eligibility Traces | Ch 7 (Sutton & Barto) | HW 3 | HW 2 |
| Sep 28 (Week 6) Supervised Learning | Nearest neighbor methods, Regression, Locally weighted regression | Section 18.6 in Russell & Norvig | Checkpoint 2. Oral reports: Pacman, Meeting: Mario, Magic, Photo |
|
| Sep 30 | Logistic regression, Introduction to Neural Networks |
18.6.4, 18.7 | ||
| Oct 5 (Week 7) | Training the network, Backprop |
HW 3 | ||
| Oct 7 | Backprop | HW 4 | Checkpoint 3 Oral reports: TBA Meeting: Roomba, Pacman, Ecology, Humanoid, Starcraft
|
|
| Oct 12 (Week 8) | Backprop
|
|||
| Oct 14 | Advanced topics in neural nets including function approximation with RL |
RL/NN (see RL Book 11.1), also 8.1-8.4 in RL book | HW 4 (due on Friday) | |
Oct 19 (Week 9) General techniques |
Function approximation with RL | HW 5 | Checkpoint 4 Oral reports: Humanoid, Roomba, Mario, Magic, Meeting: Starcraft, Ecology, Photo |
|
| Oct 21 | Overfitting/Model Complexity | 18.3.5 | ||
| Oct 26 (Week 10) Graphical Models | Introduction to Bayesian Networks
|
14.1-14.2 |
HW 5 | |
| Oct 28 | Oral checkpoints | Checkpoint 5: Oral: Starcraft, Ecology, Photos Meeting: humanoid, pacman, roomba, magic, mario
|
||
| Nov 2 (Week 11) | Using Bayes Nets for Inference |
14.2 | ||
| Nov 4 | Using Bayes Nets for Inference | |||
| Nov 9 (Week 12) | Conditional Independence | 14.3 | Checkpoint 6
|
|
| Nov 11 | Homework 6 in class | |||
| Nov 16 (Week 13) | Naive Bayes | Ch 8 (Mitchell sample chapter) | ||
| Nov 18 | Hybrid networks, Mixture models, | 14.3 |
HW 7 | |
| Nov 23 (Week 14) | Expectation Maximization | 20.3 | Preliminary writeup | |
| Nov 25 | Thanksgiving vacation |
|||
| Nov 30 (Week 15) | EM for Bayesian Networks (learning structure) | 20.3.2 | Peer reviews | |
| Dec 2 | Ensemble methods | 18.10 | HW 8 | HW 7 |
| Dec 7 (Week 16) | SVMs |
18.9 | ||
| Dec 9 | SVMs |
HW 8 | ||
| December 10, 2-5pm | Poster session |
|||
| Dec 15, 1:30-3:30 | Final writeup due |
|||