| 3/29 |
Lecture 1
|
- Introduction.
Class Notes
|
|
| 3/31 |
Lecture 2
|
- Supervised learning setup. LMS.
|
Class Notes
- Supervised Learning[pdf](Sections 1-3)
- Live Lecture Notes (draft)[pdf]
|
| 3/31 |
Assignment |
Problem Set 0 released.
|
| 4/2 |
Section 1
|
- Friday TA Lecture: Linear Algebra Review.
|
Notes
- Linear Algebra Review and Reference [pdf]
- Linear Algebra, Multivariable Calculus,
and Modern Applications
(Stanford Math 51 course text) [pdf]
- Friday Section Slides [pdf]
|
| 4/5 |
Lecture 3
|
- Weighted Least Squares. Logistic regression. Newton's Method.
|
Class Notes
- Supervised Learning [pdf] (Sections 4, 5, and 7)
- Live Lecture Notes (draft)[pdf]
|
| 4/7 |
Lecture 4
|
- Dataset split; Exponential family. Generalized Linear Models.
|
Class Notes
- Supervised Learning [pdf] (Sections 6, 8, and 9)
- Live Lecture Notes (draft)[pdf]
|
| 4/7 |
Assignment |
Problem Set 1 will be released. Due Wednesday, 4/21 at 11:59pm
|
| 4/9 |
Section 2
|
- Friday TA Lecture: Probability Theory Review.
|
Notes
- Probability Theory Review [pdf]
- The Multivariate Gaussian Distribution [pdf]
- More on Gaussian Distributions [pdf]
- Friday Section Slides [pdf]
|
| 4/12 |
Lecture 5
|
- Gaussian discriminant analysis. Naive Bayes.
|
Class Notes
- Generative Algorithms [pdf] (Section 1)
- Live Lecture Notes [pdf]
|
| 4/14 |
Lecture 6
|
- Naive Bayes, Laplace Smoothing.
|
Class Notes
- Naive Bayes and Laplace Smoothing [pdf] (Section 2)
- Live Lecture Notes [pdf]
|
| 4/16 |
Project |
Project proposal due 4/16 at 11:59pm. |
| 4/16 |
Section 3
|
- Friday TA Lecture: Python/Numpy Tutorial.
|
Notes
|
| 4/19 |
Lecture 7
|
|
Class Notes
- Kernel Methods [pdf]
- Live Lecture Notes [pdf]
|
| 4/21 |
Lecture 8
|
|
Class Notes
- Deep Learning [pdf]
- Live Lecture Notes [pdf]
|
| 4/21 |
Assignment |
Problem Set 2 will be released. Due Wednesday, 5/5 at 11:59pm
|
| 4/23 |
Section 4
|
- Friday TA Lecture: Evaluation Metrics.
|
Notes
- Friday Section Slides [pdf]
|
| 4/26 |
Lecture 9
|
- Neural Networks 2. Backpropagation.
|
Class Notes
- Deep Learning [pdf]
- Live Lecture Notes [pdf]
|
| 4/28 |
Lecture 10
|
- Bias - Variance. Regularization. Feature / Model selection.
|
Class Notes
- Regularization and Model Selection [pdf]
- Some Calculations from Bias Variance (Addendum) [pdf]
- Bias-Variance and Error Analysis (Addendum) [pdf]
- Live Lecture Notes [pdf]
|
| 4/30 |
Section 5
|
- Friday TA Lecture: Deep Learning (ConvNets).
|
Notes
- Friday Section Slides [pdf, ppt]
|
| 5/3 |
Lecture 11
|
- K-Means. GMM (non EM). Expectation Maximization.
|
Class Notes
- Unsupervised Learning, k-means clustering. [pdf]
- Mixture of Gaussians [pdf]
- The EM Algorithm [pdf]
- Live Lecture Notes (draft)[pdf]
|
| 5/5 |
Lecture 12
|
- GMM (EM). Factor Analysis.
|
Class Notes
- Lagrange Multipliers Review [pdf]
- Factor Analysis [pdf]
- Live Lecture Notes (draft)[pdf]
- Addendum Notes[pdf]
|
| 5/5 |
Assignment |
Problem Set 3 will be released. Due Wednesday, 5/19 at 11:59pm
|
| 5/7 |
Project |
Project milestones due 5/7 at 11:59pm. |
| 5/7 |
Section 6
|
- Friday TA Lecture: Midterm Review.
|
|
| 5/10 |
Lecture 13
|
|
Class Notes
- Principal Components Analysis [pdf]
- Independent Component Analysis [pdf]
- Live Lecture Notes (draft)[pdf]
|
| 5/12 |
Lecture 14
|
- Weak supervised / unsupervised learning.
|
Class Notes
- Introduction to weak supervision [slides]
- ICA and weak supervision [draft]
|
| 5/13 |
Midterm |
The midterm details TBD.
|
| 5/14 |
Section 7
|
- Friday TA Lecture: Decision Trees + Boosting.
|
Notes
|
| 5/17 |
Lecture 15
|
- Self-supervised learning (Language Models & Image Models).
|
Class Notes
- Self-Supervised Learning [slides]
|
| 5/19 |
Lecture 16
|
|
Class Notes
|
| 5/19 |
Assignment |
Problem Set 4 will be released. Due Friday, 5/28 at 11:59pm
|
| 5/21 |
Section 8
|
- Friday TA Lecture: On Critiques of ML.
|
Notes
- Technical and Societal Critiques of ML [pdf]
|
| 5/24 |
Lecture 17
|
- Basic concepts in RL, value iteration, policy iteration.
|
Class Notes
- Basic RL concepts, value iterations, policy iteration [pdf] (Sections 1 and 2)
- Live Lecture Notes [pdf]
|
| 5/26 |
Lecture 18
|
- Model-based RL, value function approximator.
|
Class Notes
- Model-based RL and value function approximation [pdf] (Sections 3 and 4)
- Live Lecture Notes [pdf]
|
| 5/28 |
Section 9
|
- Friday TA Lecture: Learning Theory (cancelled).
|
Class Notes
|
| 6/2 |
Lecture 19
|
|
|
| 6/2 |
Project |
Project final report + poster (optional) due 6/2 at 11:59pm. |
Other Resources
- All lecture videos can be accessed through Canvas.
- Advice on applying machine learning: Slides from Andrew's lecture on getting machine learning algorithms to work in practice can be found here.
- Previous projects: A list of last year's final projects can be found here.
- Data: Here is the UCI Machine learning repository, which contains a large collection of standard datasets for testing learning algorithms. If you want to see examples of recent work in machine learning, start by taking a look at the conferences NeurIPS (all old NeurIPS papers are online) and ICML. Some other related conferences include UAI, AAAI, IJCAI.
- Viewing PostScript and PDF files: Depending on the computer you are using, you may be able to download a PostScript viewer or PDF viewer for it if you don't already have one.
- Machine learning study guides tailored to CS 229 by Afshine Amidi and Shervine Amidi.
|