ECE 364: Programming Methods for Machine Learning (Fall 2026)

Course Information

In this course, you will learn how to use auto-differentiation tools like PyTorch, how to leverage them for various machine learning algorithms (linear regression, logistic regression, deep nets, Transformers, etc.), and how to extend them with custom methods to fit your needs. Auto-differentiation is one of the most important tools for data analysis and a solid understanding is increasingly important in many disciplines. In contrast to existing courses that focus on algorithmic and theoretical aspects, here we focus on studying material that permits deploying auto-diff tools to your area of interest.

Pre-requisites: Math 257 (Linear Algebra with Computational Applications) or equivalent, basic probability, and proficiency in Python.

Recommended Reference Texts: (1) Pattern Recognition and Machine Learning by Christopher Bishop
(2) Machine Learning: A Probabilistic Perspective by Kevin Murphy
(3) Deep Learning by Ian Goodfellow and Yoshua Bengio and Aaron Courville

Please note that these books are more comprehensive than the material covered in this class.

Course Deliverables:
(1) Homeworks (submission on Gradescope).
(2) Midterm Exams: There will be two midterm exams.
(3) Final Project

Final Project:

Due Date: TBD

Homework:

Homeworks are all submitted on Gradescope. We will drop the lowest homework grade (1 assignment) for each student. Late submissions will be deducted 20% per day (i.e. 20/24 % per hour late) that the assignment is submitted late. 

AI Usage Policy

Generative AI tools, such as ChatGPT, Microsoft Copilot, and Gemini, can answer questions and generate text, images, and other media. The appropriate use of generative AI varies from course to course. In ECE 364 there are times when generative AI may be useful in the course and other times where we prohibit the use of generative AI. Specifically, you MAY use generative AI in ECE 364 to:

• Aid your studying and preparation for exams, e.g. generating additional practice problems, verifying your solutions to other example problems, and checking your own understanding of course concepts.
• Help verify your own solutions when completing homework assignments.
• Generate parts of code on assignments or to verify your own written code. Such use of AI for writing code must be attributed in your homework submission.

You MAY NOT use generative AI in ECE 364 to:

• Complete any quizzes or exams.
• Fully copy/plagiarize generative AI solutions for written problems on homework assignments. Solutions on such written problems that are direct copies of answers from a Generative AI tool may be subject to disciplinary action such as a FAIR allegation.

If you have a question about the use of generative AI, please feel free to reach out to Prof. Snyder.  Failure to abide by these guidelines is a violation of academic integrity. We will investigate suspected uses of generative AI that do not follow these guidelines and apply sanctions as outlined in the University of Illinois Student Code.

Grading:

25% Homeworks; 25% Midterm 1; 25% Midterm 2; 25% Final Project

Office Hours

Lectures

Lecture Recordings

Mediaspace Recordings Link

The below syllabus is subject to minor changes.