The following is a preliminary schedule of the lectures and presentations for CS 4033/5033 Machine Learning for Fall 2019. 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.
| Date | Topic | Assigned Reading | Assigned today | Due today |
Week 1: Introduction |
||||
| Aug 19 | Overview of the course. What is machine learning? What will I learn if I take this class? | Elements of Statistical Learning (ESL), Chapter 1 | Pretest (in class) | |
Aug 21
|
Project introduction, Introduction to ML & Reinforcement learning , Exploration & Exploitation | Sutton & Barto: Chapters 1 & 2 | Projects | |
Week 2: Reinforcment Learning |
||||
| Aug 26 | The RL problem | Sutton & Barto: Chapter 3 | HW 1 | |
| Aug 28 | The RL Problem | |||
Week 3: Reinforcment Learning |
||||
| Sep 2 | Labor Day (no class)
|
|||
| Sep 4 | In-class RL project proposals |
In-class RL project proposals HW 1 |
||
Week 4: Reinforcement learning |
||||
| Sep 9 | RL problem | Written RL project proposals | ||
| Sep 11 | RL Problem, TD learning, Q-learning |
Sutton & Barto: Chapter 6 | HW 2 | |
Week 5: Reinforcment learning |
||||
| Sep 16 | TD learning, Q-learning |
|
||
| Sep 18 | RL using function approximation |
Sutton & Barto: Chapter 9 |
||
Week 6: Supervised learning |
||||
Sep 23 | Eligibility Traces |
Sutton & Barto: Chapter 7 and 12 |
HW 2 |
|
| Sep 25 | Introduction to SL, Nearest Neighbor, K-means clustering Least Squares Linear Regression, Logistic regression, Introduction to regularization |
ESL Chapter 2.1-2.3, ESL Chapter 3.1-3.2 Logistic: Wikipedia and ESL Chapter 4.4 |
HW 3 | |
Week 7: Model evaluation and short RL projects |
||||
Sep 30 |
Ridge, Lasso, and Elastic nets, Overfitting, Bias-Variance Tradeoff, Model selection |
Ridge/Lasso/Elastic: ESL Chapter 3.3-3.8 |
||
Oct 2 |
In-class Short RL project presentations Model evaluation and verification |
ESL Chapter 7 | Short RL project presentations Long RL checkpoint HW 3: Friday Oct 4 |
|
Week 8: Short RL projects, model verification |
||||
| Oct 7 | In-class Short RL project presentations Finish Model evaluation and verification |
|
HW 4 (one question) | Written Short RL projects |
| Oct 9 | In-class Long SL Project Proposals |
HW 5 | Long SL Project Proposals |
|
Week 9: Trees |
||||
Oct 14 |
Break |
|
Written Long SL project proposals |
|
| Oct 16 | Decision trees |
Trees: ESL Chapter 9.2 |
HW 4 | |
Week 10: Tree-based methods and Ensembles |
||||
Oct 21 |
Trees and random forests |
Boosting/Bagging/Ensembling: ESL Chapter 8.7, ESL Chapter 10, ESL Chapter 15 | HW 6 | HW 5 |
Oct 23 |
Ensemble methods, Boosting, Bagging, Random Forests and Gradient Boosted Regression Trees |
|
||
Week 11: Long RL projects |
||||
| Oct 28 | In-class Long RL project presentations |
Long RL project presentations | ||
Oct 30 |
In-class Long RL project presentations |
|
||
Week 12: Neural Nets, Deep learning |
||||
| Nov 4 | Neural Networks, Backpropagation |
Written long RL projects |
||
| Nov 6 | Online Short SL project proposals Neural Networks, Backpropagation, CNNs |
Short SL project proposals Long SL checkpoint HW 6 (Nov 7) |
||
Week 13: Deep learning |
||||
| Nov 11 | Convolutional Neural Nets/Deep learning |
|
Written SL short project proposals | |
| Nov 13 | Naive Bayes, Bayesian Networks | HW 7 | ||
Week 14: Deep learning and deep RL |
||||
| Nov 18 | Expectation Maximization |
ESL 8.5 |
|
|
| Nov 20 | Kernel methods, Kernel trick, SVR, SVMs |
|||
Week 15: Bayes and feature importance |
||||
| Nov 25 | Feature importance, learning how to interpret ML models. |
HW 7 | ||
| Nov 27 |
Thanksgiving vacation |
|||
Week 16: Kernel methods, SVR, SVM |
||||
| Dec 2 | Deep RL: Emergent Tool Use from Multi-Agent Interaction | |||
| Dec 4 | Deep RL: AlphaZero | AlphaZero paper | ||
Week 17: Final |
||||
| Dec 10, 4:30-6:30 | Final project writeup due |
|||