Syllabus and Course Schedule

[Previous offerings: Spring 2020, Summer 2020]


This table will be updated regularly through the quarter to reflect what was covered, along with corresponding readings and notes.
DateEventDescriptionMaterials and Assignments
9/14 Lecture 1
  • Introduction.
9/16 Lecture 2
  • Supervised learning setup. LMS.
Class Notes
  • Supervised Learning [pdf](Sections 1-3)
9/16 Assignment Problem Set 0 released. Due Tuesday, 9/22 at 11:59pm
9/19 Section 1
  • Friday TA Lecture: Linear Algebra Review.
Class Notes
  • Review of Linear Algebra [pdf]
  • Linear Algebra Review and Reference [pdf]
Prerequisite Reading
  • Linear Algebra, Multivariable Calculus,
    and Modern Applications
    (Stanford Math 51 course text) [pdf]
9/21 Lecture 3
  • Weighted Least Squares. Logistic regression. Newton's Method.
Class Notes
  • Supervised Learning [pdf] (Sections 4, 5, and 7)
9/23 Lecture 4
  • Perceptron. Exponential family. Generalized Linear Models.
Class Notes
  • Supervised Learning [pdf] (Sections 6, 8, and 9)
9/23 Assignment Problem Set 1 will be released. Due Wednesday, 10/7 at 11:59pm
9/25 Section 2
  • Friday TA Lecture: Probability Theory Review.
  • Probability Theory Review [pdf]
  • The Multivariate Gaussian Distribution [pdf]
  • More on Gaussian Distribution [pdf]
  • Section slides [pdf]
  • 9/28 Lecture 5
    • Gaussian discriminant analysis.
    Class Notes
    • Generative Algorithms [pdf] (Section 1)
    9/30 Lecture 6
    • Naive Bayes, Laplace Smoothing.
    Class Notes
    • Naive Bayes and Laplace Smoothing [pdf] (Section 2)
    10/2 Section 3
    • Friday TA Lecture: Python/Numpy Tutorial.
  • Slides [pdf]
  • Python Tutorial Notebook [link, jupyter notebook]
  • 10/2 Project Project proposal due 10/2 at 11:59pm.
    10/5 Lecture 7
    • Kernels.
    Class Notes
    • Kernel Methods [pdf]
    10/7 Lecture 8
    • Neural Networks 1.
    Class Notes
    • Deep Learning [pdf]
    10/7 Assignment Problem Set 2 will be released. Due Wednesday, 10/21 at 11:59pm
    10/9 Section 4
    • Friday TA Lecture: Deep Learning.
  • Slides [pdf]
  • 10/12 Lecture 9
    • Neural Networks 2. Backpropagation.
    Class Notes
    • Deep Learning [pdf]
    10/14 Lecture 10
    • Bias - Variance. Regularization. Feature / Model selection.
    Class Notes
    • Bias - Variance [pdf]
    • Regularization and Model Selection [pdf]
    • Some Calculations from Bias Variance (Addendum) [pdf]
    • Bias-Variance and Error Analysis (Addendum) [pdf]
    • Double Descent (Optional Reading) [link]
    • Hyperparmeter Tuning and Cross Validation [canvas video]
    10/16 Section 5
    • Friday TA Lecture: Evaluation Metrics.
  • Slides [pdf]
  • 10/19 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 (spring quarter) [old draft]
    10/21 Lecture 12
    • GMM (EM). Factor Analysis.
    Class Notes
    • Lagrange Multipliers Review [pdf]
    • Factor Analysis [pdf]
    • Live lecture notes [draft]
    10/21 Assignment Problem Set 3 will be released. Due Wednesday, 11/4 at 11:59pm
    10/23 Section 6
    • Friday TA Lecture: Midterm Review.
  • Slides [pdf]
  • 10/23 Project Project milestones due 10/23 at 11:59pm.
    10/26 Lecture 13
    • PCA, ICA.
    Class Notes
    • Principal Components Analysis [pdf]
    • Independent Component Analysis [pdf]
    • Live lecture notes (spring quarter) [old draft, in lecture]
    10/28 Lecture 14
    • Weak supervised / unsupervised learning.
    Class Notes
    10/29 Midterm The midterm details TBD.
    11/2 Lecture 15
    • ML advice.
    Class Notes
    • ML advice [pdf]
    11/4 Lecture 16
    • Advice for applying machine learning.
    Class Notes
    • Advice for applying machine learning. [pdf]
    11/4 Assignment Problem Set 4 will be released. Due Wednesday, 11/18 at 11:59pm
    11/9 Lecture 17
    • Basic RL concepts, value iterations, policy iteration.
    Class Notes
    • Basic RL concepts, value iterations, policy iteration [pdf] (Sections 1 and 2)
    11/11 Lecture 18
    • Model-based RL and value function approximation.
    Class Notes
    • Model-based RL and value function approximation [pdf] (Sections 3 and 4)
    11/16 Lecture 19
    • Policy search. REINFORCE.
    Class Notes
    • REINFORCE [pdf]
    11/18 Lecture 20
    • Societal impact.
    11/18 Project Project final report due 11/18 at 11:59pm.
    Other Resources
    1. All lecture videos can be accessed through Canvas.
    2. Advice on applying machine learning: Slides from Andrew's lecture on getting machine learning algorithms to work in practice can be found here.
    3. Previous projects: A list of last year's final projects can be found here.
    4. 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.
    5. 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.
    6. Machine learning study guides tailored to CS 229 by Afshine Amidi and Shervine Amidi.