Introduction to Machine Learning
(Spring 2025)

Pre-semester Information

👋 Hi there! Welcome to 6.390 -- we're very much looking forward to working with you all this spring!

1) Course Overview §

6.390 introduces the principles and algorithms of machine learning from an optimization perspective. Topics include linear and non-linear models for supervised, unsupervised, and reinforcement learning, with a focus on gradient-based methods and neural-network architectures. Enrollment may be limited.

2) Prerequisites §

Concretely, things we expect you to know (we use these constantly, but don’t teach them explicitly):

2.1) Programming §

  • Intermediate Python, including the notion of classes.
  • Exposure to algorithms – ability to understand & discuss pseudo-code, and implement in Python.

2.2) Linear Algebra §

  • Fundamental matrix concepts and manipulations, e.g., rank, multiplication, and inverse.
  • Points and planes in high-dimensional space.
  • Basic matrix calculus, e.g., gradients.

6.1010 or 6.1210 can serve as the programming prerequisite. 18.06, 18.C06, 18.03, or 18.700 can serve as the linear algebra prerequisite.

(For each of these courses above, a link points to a representative syllabus from some past semesters, for reference.)

3) Class Meeting and Sections §

We will be meeting for Lectures on Fridays, Recitations on Mondays, and Labs on Wednesdays.

3.1) Lectures §

Friday lectures focus to anchor the upcoming week's discussion, overview the technical contents, and tie together the high-level motivations, concepts, and stories. Along with lecture notes, they prepare students for the upcoming Monday recitations and Wednesday labs.

Lectures will be held class-wide, in Room 10-250, Fridays 11am-12pm. Recordings will be made available shortly after live sessions. Our first lecture will be on Friday, Feb. 7.

3.2) Recitation and Lab sections §

Monday recitations focus on discussing examples and working through pen-paper problems. Wednesday labs engage students with each other in small teams (typically two to three students per team) and with staff, to explore fundamental concepts.

Recitations and Labs will be held in small sections. We have seven sections planned. Each student will be assigned into one section.

    Section Time Room
    1 Mon & Wed, 9:30am-11am 34-501
    2 Mon & Wed, 9:30am-11am 32-044
    3 Mon & Wed, 11am-12:30pm 34-501
    4 Mon & Wed, 11am-12:30pm 32-044
    5 Mon & Wed, 1pm-2:30pm 34-501
    6 Mon & Wed, 1pm-2:30pm 32-044
    7 Mon & Wed, 2:30pm-4pm 34-501

First class meeting

Our first class meeting will be a Recitation on Monday, Feb. 3.

Section assignments and a self-switch mechanism will be detailed here on Friday, Jan. 31.

4) Cross-registration §

  • We appreicate your interest in the course. Due to limited capacity, cross-registration requests will be considered after MIT pre-registration ends on January 16, 2025. Official requests need to be initiated with the Harvard/Wellesley Registrar. Please also be sure to fill out this form here to join our course waitlist. If we are able to approve your request, we will respond by Friday, January 31.

  • We follow MIT's Academic Calendar, and do not have additional extensions or accommodations based on home university calendar. Especially important will be for you to plan ahead for our two in-person exams.

  • We'll have a midterm exam during the week of March 17–21 (exact time and location to be finalized). We'll also have a final exam during MIT's final exam period, Friday, May 16 through Wednesday, May 21; the final exam is to be scheduled by the Registrar.

  • If you're not familiar with MIT campus, you might find the whereis site helpful.

5) Listeners §

Due to capacity and other constraints, we will not accept Listener registrants in 6.390 this semester.

6) Course Number Change§

Since fall22, all MIT EECS (Course 6) subjects have been renumbered (rationale and details can be found here). This subject used to be called 6.036; moving forward, we'll refer to it internally as 6.390 ("six three-nine-oh"). But for registration purposes, please register for 6.3900 (note the extra zero).

7) Other Questions?§

Feel free to drop us an email at 6.390-inquiry@mit.edu. We'd love to hear from you!