Basic Information About 6.390
Please Log In for full access to the web site.
Note that this link will take you to an external site (https://shimmer-mit-edu.ezproxy.canberra.edu.au) to authenticate, and then you will be redirected back to this page.
Table of Contents
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) Course Components§
3.1) Exercises§
Online exercises are typically released on Wednesday (available and completed through the course website) 5pm, and will be due the following Monday by 9am.
The intention is for you to read the lecture notes and/or viewed the Friday lectures, and do these exercises, so as to maximize the value of your participation in the upcoming recitation, and to begin learning the material in advance of the next lab and homework.
3.2) Lectures§
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, and the exercises, they prepare students for the upcoming Monday recitations and Wednesday labs.Lectures will be held class-wide, in Room 45-230, Fridays 12pm-1pm. No attendance will be taken. Recordings will be made available shortly after live sessions.
3.3) Recitations§
The Monday section meeting will be Recitation, focused on discussing examples and working through interesting problems. The Wednesday section meeting will be a Lab assignment that you work through with a student partner and get in-lab checkoffs on.Seven sections are offered:
| Section | Time | Room | Instructor |
|---|---|---|---|
| 1 | 9:30am-11am | 34-501 | Ike Chuang |
| 2 | 9:30am-11am | 32-044 | Bruce Tidor |
| 3 | 11am-12:30pm | 34-501 | Tess Smidt |
| 4 | 11am-12:30pm | 32-044 | Mardavij Roozbehani |
| 5 | 1pm-2:30pm | 34-501 | Shen Shen |
| 6 | 1pm-2:30pm | 32-044 | Alexandre Megretski |
| 7 | 2:30pm-4pm | 34-501 | Pete Szolovits |
Recitations will be at the specified location and time on Mondays, and will be synchronous. You may only attend your officially assigned Recitation section. Your Lab section number (and meeting time and location) will be the same as your Recitation section number, on the following Wednesday. If you are sick, please do not attend recitation or lab; for illness or personal situations, see the guidelines below.
3.4) Labs§
Each student must attend a weekly 1.5 hour lab session on Wednesday. You must attend the same section for recitation and lab. The lab session will be synchronous. We will be using the lab to engage students with each other in small teams (typically two to three students per team) and with staff, to explore fundamental concepts in advance of individual work in the homeworks.
You may only attend your officially assigned lab section. Typically, each lab will require a "checkoff" --a brief discussion with a staff member on the topic of the assigned problems. The checkoff is generally expected to be completed by the end of the lab section meeting; however, the checkoff can be completed by the lab deadline (generally Monday 11pm Eastern after the lab section) in office hours without late penalty. If you are sick, please do not attend lab; For illness or personal situations, see the guidelines below.
3.5) Homeworks§
Homework is generally released each Monday at 9am Eastern, and is due online (through the course website) the following Wednesday at 11pm Eastern.
3.6) Midterm and Final Exam§
Both the midterm and final exams will be in-person, written exams.
The Midterm Exam will be on Wednesday, 23 October 2024, from 7:30pm-9:30pm. The final exam, as scheduled by the registrar, will be Friday 20 December 2024, 9am-noon, at the Johnson Track.
4) Getting help on 6.390§
Please follow this guideline when asking for help (and note that the best way to get help depends on the kind of question you have).
5) Illness and personal issues§
Please refer to the Grading page for more info.6) Listeners§
Due to capacity and other constraints, we will not accept Listener registrants in 6.390 this semester. We are sorry about that, and can offer, as an alternative, the complete course material from four years ago, including lectures, readings, and online homework.