CS446/ECE449: Machine Learning (Spring 2026)
Course Information
Course Description: This course will cover the fundamental concepts, theory and algorithms in machine learning, including (1) supervised learning, (2) unsupervised learning, and (3) reinforcement learning. We will also discuss thetheoretical foundations of machine learning, such as PAC learning theory; as well as state-of-the-art machine learning techniques, such as deep learning, generative models, and large language models (LLMs). The course will beself-contained, and existing knowledge about machine learning algorithms is preferred but notrequired. Prerequisites include probability and statistics, linear algebra and calculus.Pre-requisites: Probability, linear algebra, and proficiency in Python.
Recommended Text:
(1) Probabilistic Machine Learning: An Introduction [KM]
(2) Deep Learning [GBC]
(3) Understanding Machine Learning: From Theory to Algorithms [SB]
(4) The Elements of Statistical Learning: Data Mining, Inference, and Prediction [HTF]
(5) Deep Learning: Foundations and Concepts [BB]
(6) Reinforcement Learning: an Introduction [SB+]
Course Deliverables:
(1) 5 sets of ungraded homework
(2) 5 in-class quizzes (closed-book, questions similar to those in homework)
(4) Midterm and Final exams (closed-book, one page hand-written cheatsheet allowed)
Grading:
3 credit: Quizzes 50% (drop 1 lowest), MPs 10% (drop 1 lowest), Midterm 20%, Final 20%
4 credit: Quizzes 50% (no drop), MPs 10% (must do both), Midterm 20%, Final 20%
Grading policy is subject to change.
Late Policy: MPs are due on 11:59 pm CT on the due date. Each student will have a 3-day grace period in total for the two MPs. You may use this grace period for any MP assignment throughout the semester. After the grace period, late MP submission will be penalized 20% per day. Students with legitimate reasons (e.g., medical) who contact the professor before the deadline may apply for an extension (typically, you will need an signed doctor's note, or an official Absence Letter obtained from Office of the Dean of Students).
Generative AI Policy: The use of generative AI tools (e.g., ChatGPT, Claude, Copilot) is allowed and encouraged to support your learning in this course. Homework assignments will not be graded. You are welcome to use generative AI to work through problems, obtain personalized explanations, and deepen your understanding. However, please keep in mind that AI tools may produce incorrect or misleading information, so please approach their output with critical thinking and verification. The ultimate goal is to help you grasp new knowledge and develop problem-solving skills; using AI responsibly is part of your learning process. Quizzes will be closed-book and administered without AI assistance to assess your individual understanding of course material.
For MPs, you are encouraged to use generative AI to assist with programming tasks. The instructor believes that it is an essential skill for today's student to collaborate with AI tools to improve their productivity. However, please be aware that AI-generated code may contain errors or may not fully address the complexity of the assignment, and you must be responsible for debugging, testing, and ensuring correctness, and should be prepared to explain your implementation choices and code functionality.
All UIUC students have free access to Microsoft Copilot (log in with your NetID) with advanced AI models (e.g., GPT-5.2 thinking). While AI tools are permitted, you must engage meaningfully with the material. Using AI should enhance your learning, not replace it. If you have questions about appropriate use, please ask.
Instructor & TAs
Huan Zhang
InstructorEmail: huanz[at]illinois.edu
Vishesh Prasad
Head Teaching AssistantEmail: vprasad3[at]illinois.edu
Shanbin Sun
Teaching AssistantEmail: shanbin3[at]illinois.edu
Junsheng Huang
Teaching AssistantEmail:jh103[at]illinois.edu
Yuxi Chen
Teaching AssistantEmail: yuxi5[at]illinois.edu
Logistics
Class Time: Tuesday, Thursday 12:30pm-1:45pmLocation: 1320 DCL
Homework / MPs: Gradescope (check the first lecture slides for code)
Course announcements and discussions: Piazza (check the first lecture slides for code)
TA Office Hours:
Vishesh Prasad (Head TA): Wednesday 2 - 3 pmShanbin Sun: Monday 2 - 3 pm
Yuxi Chen: Friday 11 am - 12 pm Office Hours location: ECEB2036
Instructor Office Hours: Thursday 6 - 6:30 pm (in-person), Friday 5:15 pm - 5:45 pm (zoom). Advanced booking required (click the link to book).
Lectures
| Event | Date | Description | Slides | HW | Readings | |
|---|---|---|---|---|---|---|
| Lecture 1 | Jan 20 | Introduction, KNN | [Slides] | |||
| Lecture 2 | Jan 22 | Probability Review, Naive Bayes | [Slides] |
|
||
| Lecture 3 | Jan 27 | Intro to Optimization | [Slides] | [GBC] Chapter 4.3, 4,4; [BB] Chapter 7.2, 7.3 | ||
| Lecture 4 | Jan 29 | Linear Regression | [Slides] | [KM] Chapter 11.1, 11.2 | ||
| HW 1 released | Jan 29 | Covers Lecture 1 - 5 (no due date, ungraded) | [HW] [Sol] | |||
| Lecture 5 | Feb 3 | Logistic Regression | [KM] Chapter 10.1, 10.2 | |||
| Lecture 6 Quiz 1 |
Feb 5 | Support Vector Machine Quiz 1 covers HW 1 materials |
[HTF] Chapter 12.2; [SB] Chapter 15.1-15.2 | |||
| Lecture 7 | Feb 10 | Kernel Methods | [SB] Chapter 16.1-16.2; [KM] Chapter 17.3.1-17.3.4 | |||
| HW 2 released | Feb 12 | Covers Lecture 6 - 9 (no due date, ungraded) | ||||
| Lecture 8 | Feb 12 | Decision Trees, Tree Ensembles | [SB] [KM] Chapter 18.1 | |||
| Lecture 9 | Feb17 | Unsupervised learning: K-Means, PCA | ||||
Lecture 10 |
Feb 19 | MLPs, Backpropagation Quiz 2 covers HW 2 materials |
||||
| Lecture 11 | Feb 24 | PyTorch Tutorial | ||||
| Lecture 12 | Feb 26 | Convolutional Neural Networks | ||||
| HW 3 released | Feb 26 | Covers Lecture 10 - 14 (no due date, ungraded) | ||||
| MP 1 released | Mar 2 | (tentative) Build your own PyTorch library from scratch | ||||
| Lecture 13 | Mar 3 | Auto-encoders / Variational Autoencoders | ||||
| Lecture 14 | Mar 5 | Sequential Models, RNNs, LSTMs | ||||
| Lecture 15 Quiz 3 |
Mar 10 | Self-supervised Learning, Contrastive Learning Quiz 3 covers HW3 materials |
||||
| Lecture 16 | Mar 12 | Course Review | ||||
| No Class | Mar 17 | Spring break | ||||
| No Class | Mar 19 | Spring break | ||||
| Exam | Mar 24 | Mid-term Exam (in class) | ||||
| Lecture 17 | Mar 26 | Attention, Transformers | ||||
| MP 1 Due | Mar 29 | MP 1 Due at 11:59 pm CT | ||||
| Lecture 18 | Mar 31 | Large Language Models 1 | ||||
| HW4 released | April 2 | Covers Lecture 15 - 20 (no due date, ungraded) | ||||
| Lecture 19 | April 2 | Large Language Models 2 | ||||
| MP 2 released | April 6 | (tentative) Build your own language model from scratch | ||||
| Lecture 20 | April 7 | Diffusion Models | [BB] Chapter 20 | |||
| Lecture 21 Quiz 4 |
April 9 | Learning Theory 1 Quiz 4 covers HW4 materials |
[SB] Chapter 2.1-2.2 | |||
| Lecture 22 | April 14 | Learning Theory 2 | [SB] Chapter 2.3, Chapter 3, 4 | |||
| Lecture 23 | April 16 | Markov Decision Process | [SB+] Chapter 1, Chapter 3.1-3.5 | |||
| HW 5 released | April 21 | Covers Lecture 21 - 25 (no due date, ungraded) | ||||
| Lecture 24 | April 21 | Value iteration, Q-Learning | [SB+] Chapter 4.1-4.4 | |||
| Lecture 25 | April 23 | Policy Gradient | [SB+] Chapter 6.5, Chapter 13 | |||
| Lecture 26 Quiz 5 |
April 28 | Deep Reinforcement Learning, RL for LLMs, Reasoning Quiz 5 covers HW5 materials |
||||
| Lecture 27 | April 30 | AI Agents and Agentic AI | ||||
| MP 2 Due | May 3 | MP 2 Due at 11:59 pm CT | ||||
| Lecture 28 | May 5 | Course Review | ||||
| Exam | TBD | Final Exam |
