DS 3000A/9000A: Intro to Machine Learning (F2026)
Detailed course information is on OWL Brightspace.
Sections
| Section | Lectures | Labs | Instructor | TAs |
|---|---|---|---|---|
| 001 | Tuesdays, 3:30-5:30 PM | Thursdays, 3:30-5:30 PM | Agustinus Kristiadi | TBA |
| 011 | Mondays, 6:30-8:30 PM | Wednesdays, 6:30-8:30 PM | Dan Lizotte | TBA |
On OWL, go to Calendar at the top purple bar, then click Subscribe, and add the URL to your calendar app (e.g. Outlook).
The dates in the table below is just for reference.
Schedule
Read the assigned reading materials (see table) before the lecture each week. They will only take ~30 minutes to read. Extensive reading is not expected; it's normal to not understand on your first reading.
The notation such as "[ISL] 9.1–9.2" means "Chapters 9.1 to 9.2 (inclusive) of the [ISL] textbook, including all subsections, e.g., 9.1.2". Meanwhile, "[PRML] 9.2.0" (i.e., with zero at the end) means "Section 9.2 of the [PRML] textbook, without its subsections, i.e., without 9.2.1, etc.".
| Week | Week Of | Topic | Readings |
|---|---|---|---|
| 1 | Sep 7 | Introduction, admins, review Assignment 1 released | [LA]; [PY]; [D2L] 2.3–2.4; [PRML] 1.0–1.1 |
| 2 | Sep 14 | Linear regression Assignment 1 due Assignment 2 released | [ISL] 2.1.0–2.1.2; [PRML] 3.1.0–3.1.1 |
| 3 | Sep 21 | Probability & maximum likelihood Assignment 2 due Assignment 3 released | [PROB]; [D2L] 2.6; [PRML] 1.2.4–1.2.5 |
| 4 | Sep 28 | Classification Assignment 3 due DS 9000A: Group formation deadline Assignment 4 released | [ISL] 4.1–4.3 |
| 5 | Oct 7 | Bias-variance Assignment 4 due Assignment 5 released | [PRML] 1.1; [PRML] 3.2; [ISL] 2.2.1–2.2.2 |
| 6 | Oct 11 | Reading week No lecture, no lab | All the above |
| 7 | Oct 19 | Regularization Assignment 5 due DS 9000A: Project proposal due Assignment 6 released | [PRML] 3.1.4 |
| 8 | Oct 26 | Lec: review session Lab: midterm test | All the above |
| 9 | Nov 2 | Uncertainty quantification Assignment 6 due Assignment 7 released | [PRML] 14.2; [ISL] 5.2 |
| 10 | Nov 9 | Neural networks Assignment 7 due Assignment 8 released | [D2L] 5.1–5.3; BP |
| 11 | Nov 16 | Tree-based models Assignment 8 due Assignment 9 released | [PRML] 14.3; [ISL] 8.1, 8.2.1–8.2.2 |
| 12 | Nov 23 | Dimensionality reduction Assignment 9 due Assignment 10 released | [PRML] 12.0–12.1.1 |
| 13 | Nov 30 | Clustering Assignment 10 due DS 9000A: Project final report due Assignment 11 released (ungraded) | [ISL] 12.4.1; [PRML] 9.2.0 |
Reading Materials
- [PRML] Bishop, C., Pattern Recognition and Machine Learning, Springer, 2024. [Link].
- [ISL] James, G. and Witten, D., Hastie, T., and Tibshirani, R., An Introduction to Statistical Learning with Applications in Python, Springer, 2023. [Link].
- [D2L] Zhang, A., Lipton, Z. C., Li, M., Smola, A. J., Dive into Deep Learning, Cambridge University Press, 2021. [Link].
- [BP]: Backpropagation as computational graph, Stanford CS231n. [Link].
- [LB] Kolter, "Linear Algebra Review and Reference". [Link]
- [PROB] Maleki, Do, "Review of Probability Theory". [Link]
- [PY] Johnson, "Python NumPy Tutorial". [Link]
Prerequisites
Please refer to the course outline for the full, formal prerequisites. In general, to take this course, students should have exposure to Multivariable Calculus, Linear Algebra, and Probability & Statistics.
If you have heard and learned the following concepts before, you should be able to follow this course well:
- Linear algebra: vectors, matrices, dot products.
- Probability & Statistics: Event, sample space, probability distributions, probability mass function, probability density functions.
- Multivariable calculus: partial derivatives, gradients.