Machine Learning (ECE), EECS 553, Fall 2026

The goal of machine learning is to develop computer algorithms that can learn from data or past experience to make accurate, useful, and fair predictions on new unseen data. The capabilities and successes of machine learning have grown tremendously over the last few decades, and extremely rapidly over the past few years. This progress has had major impact in many real-world applications, yet other applications have seen little to no progress. This course will give a graduate-level introduction of machine learning and provide mathematical and statistical foundations of machine learning, mathematical derivation and implementation of the algorithms, and discussion of their applications. On assignments, students will work through mathematical derivations applying principles learned in class, implement machine learning algorithms in Julia or Python, and apply those algorithms to data sets spanning a variety of applications. In small groups, students will also participate in a machine learning reproducibility challenge, which involves reproducing the results and assessing the conclusions of a paper published in a major machine learning venue.

FAQ:

What are the differences between EECS 445, 453, 545 and 553?

Starting in Fall 2022, EECS 453/553 are offered by the ECE division, whereas EECS 445/545 are offered by the CSE division. Both 545 and 553 assume familiarity with probability and linear algebra. EECS 553 expects experience with graduate coursework in linear algebra and probability, such as ECE 501 and ECE 551. The primary difference between the courses is a matter of emphasis. Both courses will cover fundamental principles, mathematical derivations, and applications to real-world examples. 445/545 place relatively more emphasis on software implementation and application to real-world data, whereas 453/553 place relatively more emphasis on mathematical derivations and principles. Both 500-level courses will serve students seeking to do research in machine learning.

Can I take 553 even if I haven't had graduate coursework in probability and linear algebra?

We discourage students who have not taken probability and linear algebra courses at the 500 level or above from taking EECS 553. If you are eager to study ML, then take EECS 453 - Principles of Machine Learning. Otherwise, first take the pre-requisite courses (especially ECE 501 and ECE 553) and then take 553 in future when you are well prepared.

The first homework assignment in 553 will include many 501/551 type problems.

If you have not taken ECE 551 at UM then you should first review the ECE 551 book, lecture notes, and homeworks to self assess whether you really have the expected background.

EECS 553 is offered every semester whereas ECE 551 is offered only Fall terms, so we recommend taking ECE 501 and 551 in the Fall, and waiting to take EECS 553 in the following Winter or Fall.

You might also want to look at CSE 592: Foundations of Artificial Intelligence and check for an EECS 598 course on ML for Engineers


There are a lot of people on the waitlist; will the class size be increased or new sections added?

There are always a lot of people on the waitlist for 545/553. A lot of students also drop in the first few weeks of the term. If the waitlist is long enough, I will seek a new classroom to ensure capacity so that no one has to be turned away, though there is always a chance that this is not possible. The department/divisions do their best to offer as many sections as possible, but any given semester we may not have capacity. This semester no new sections will be added.

Will lectures be recorded?

Yes, all lectures will be recorded using the lecture capture system.
No class sessions are planned to be synchronous on zoom. If a class needs to be on zoom for unexpected reasons, then that class will be recorded as well.

Can I take 553 along with another class/lab whose classtime overlaps, or can I take 553 "remotely"?

No. Class time will include interactive learning such as iClicker questions, for which participation is part of the grade.