Time and Location:
Monday, Wednesday 4:30-5:50pm, Bishop Auditorium
Class Videos:
Current quarter's class videos are available here for SCPD students and here for non-SCPD students.
*
We may update the course materiels. Please check for the latest version before lectures.
| Event | Date | Description | Materials and Assignments | |
|---|---|---|---|---|
| Lecture 1 | 4/1 | Introduction and Basic Concepts |
Class Notes: Introduction [pdf] |
|
| A0 | 4/3 | Problem Set 0 [pdf] [solution]. Out 4/1. Due 4/10. Submission instructions. | ||
| Lecture 2 | 4/3 | Supervised Learning Setup. Linear Regression. | Class Notes | |
| Section | 4/5 |
Discussion Section: Linear Algebra [Notes] |
||
| Lecture 3 | 4/8 |
Weighted Least Squares. Logistic Regression. Netwon's Method Perceptron. Exponential Family. Generalized Linear Models. |
Class Notes | |
| Lecture 4 | 4/10 | |||
| A1 | 4/10 |
Problem Set 1 [zip]. Out 4/10. Due 4/24. Submission instructions. |
||
| Section | 4/12 | Discussion Section: Probability [Notes][Slides] | ||
| Lecture 5 | 4/15 | Gaussian Discriminant Analysis | Class Notes | |
| Lecture 6 | 4/17 |
Naive Bayes. Laplace Smoothing. Kernel Methods. |
||
| Section | 4/19 | Discussion Section: Python [slides] | ||
| Lecture 7 | 4/22 | SVM. Kernels. | Class Notes | |
| Lecture 8 | 4/24 | Neural Network. | Class Notes | |
| A2 | 4/24 |
Problem Set 2 [zip]. Out 4/24. Due 5/8. Submission instructions. |
||
| Section | 4/26 | Discussion Section: Learning Theory [pdf] | ||
| Project | 4/26 | Project proposal due at 11:59pm. | ||
| Lecture 9 | 4/29 | Neural Network. | Class Notes | |
| Lecture 10 | 5/1 |
Bias/ Variance. Regularization. Feature/ Model selection. |
Class Notes | |
| Section | 5/3 | Discussion Section: Evaluation Metrics [Slides] | ||
| Lecture 11 | 5/6 | Practical Advice for ML projects |
Class Notes
|
|
| Lecture 12 | 5/8 | K-means. Mixture of Gaussians. Expectation Maximization. | Class Notes | |
| A3 | 5/8 |
Problem Set 3 [zip]. Out 5/8. Due 5/22. Submission instructions. |
||
| Section | 5/10 | Discussion Section: Midterm Review [pdf] | ||
| Lecture 13 | 5/13 | GMM(EM). Variational Autoencoders. |
Class Notes
|
|
| Lecture 14 | 5/15 | Principal Component Analysis. Independent Component Analysis. | Class Notes | |
| Midterm | 5/15 | We will have an in-class midterm from 7pm to 10pm. Logistics. SCPD Logistics. Practice Midterm. | ||
| Lecture 15 | 5/20 | MDPs. Bellman Equations. Value iteration and policy iteration |
Class Notes
|
|
| Lecture 16 | 5/22 | Value function approximation. | Class Notes | |
| A4 | 5/22 |
Problem Set 4 [zip]. Out 5/22. Due 6/5. Submission instructions. |
||
| Section | 5/24 | Discussion Section: Convolutional Neural Nets [pdf] | ||
| Project | 5/24 | Project milestones due 5/24 at 11:59pm. | ||
| Lecture 18 | 5/29 | Policy search. REINFORCE. |
Class Notes
|
|
| Section | 5/31 | Discussion Section: Gaussian Processes [pdf] | ||
| Lecture 19 | 6/3 | Other settings of RL, Imitation learning, Adversarial machine learning | Class Notes | |
| Lecture 20 | 6/5 | Course Review and Wrap up | Class Notes | |
| Project | 6/11 |
Project poster PDF and project recording (remote SCPD only) due at 11:59 pm Submission instructions. |
||
| Project | 6/12 | Poster presentations from 3:30-6:30pm. Venue and details to be announced. | ||
| Project | 6/12 | Final writeup due at 6:30pm (no late days). | ||
Section Notes
|
||||
Other Resources
|
||||
| Supplementary Notes | ||||