Course Description

MIT's introductory course on deep learning methods with applications to computer vision, natural language processing, biology, and more! Students will gain foundational knowledge of deep learning algorithms and get practical experience in building neural networks in TensorFlow. Course concludes with a project proposal competition with feedback from staff and panel of industry sponsors. Prerequisites assume calculus (i.e. taking derivatives) and linear algebra (i.e. matrix multiplication), we'll try to explain everything else along the way! Experience in Python is helpful but not necessary. This class is taught during MIT's IAP term by current MIT PhD researchers. Listeners are welcome!

Time and Location

Mon Jan 24 - Fri Jan 28, 2022

1:00pm - 4:00pm EST Everyday

1:00pm-1:45pm: Lecture Part 1
1:45pm-2:30pm: Lecture Part 2
2:30pm-4:00pm: Software Labs

Classes will take place physically in MIT Room TBD.


Course Schedule

New lectures, slides, and labs for 2022 are coming soon!

Intro to Deep Learning
Lecture 1
Jan. 24, 2022

[Slides] [Video] coming soon!

Deep Sequence Modeling
Lecture 2
Jan. 24, 2022

[Slides] [Video] coming soon!

Intro to TensorFlow;
Music Generation
Software Lab 1

[Code] coming soon!

Deep Computer Vision
Lecture 3
Jan. 25, 2022

[Slides] [Video] coming soon!

Deep Generative Modeling
Lecture 4
Jan. 25, 2022

[Slides] [Video] coming soon!

De-biasing Facial Recognition Systems
Software Lab 2

[Paper] [Code] coming soon!

Deep Reinforcement Learning
Lecture 5
Jan. 26, 2022

[Slides] [Video] coming soon!

Limitations and New Frontiers
Lecture 6
Jan. 26, 2022

[Slides] [Video] coming soon!

Learning End-to-End Self-Driving Control
Software Lab 3

[Code] coming soon!

Guest Lecture
Lecture 9
Jan. 27, 2022

[Slides] [Video] coming soon!

Guest Lecture
Lecture 10
Jan. 27, 2022

[Slides] [Video] coming soon!

Final Project
Work on final projects

Guest Lecture
Lecture 11
Jan. 28, 2022

[Slides] [Video] coming soon!

Guest Lecture
Lecture 12
Jan. 28, 2022

[Slides] [Video] coming soon!

Project Competition
Project pitches and final awards!

Frequently Asked Questions

For any other questions please reach out to the course staff at introtodeeplearning-staff@mit.edu.

All listeners are welcome to attend!
  • If you are an MIT student, please formally register as a listener on Websis. for instructions
  • If you are not an MIT student, you can still attend the course without registering.
6.S191 is offered as a 6 units course and graded P/D/F based on completion of project proposal assignment. Listeners also welcome!
Registration opens on Dec 1, 2021 at 9am. If you are an MIT student please register here after registration opens. You can specify if you want to take the course for credit or as a listener there.

All other MIT affiliates (postdocs, faculty, staff, etc) are very welcome to attend and participate in the course. Please sign up for the mailing list to receive updates.

After the MIT course, the course will be made publically available to non-MIT affiliates as well. Again, please sign up for the mailing list to receive updates when this occurs.

We are expecting very elementary knowledge of linear algebra and calculus. How to multiply matrices, take derivatives and apply the chain rule. Familiarity in Python is a big plus as well. The course will be beginner friendly since we have many registered students from outside of computer science.

If you would like to receive course related updates and lecture materials please subscribe to our YouTube channel and sign up for our mailing list.

All course materials available online for free but are copyrighted and licensed under the MIT license. If you are an instructor and would like to use any materials from this course (slides, labs, code), you must add the following reference to each slide:

© Alexander Amini and Ava Soleimany
MIT 6.S191: Introduction to Deep Learning
IntroToDeepLearning.com

All course materials are copyrighted and licensed under the MIT license. If you are an instructor and would like to use any materials from this course (slides, labs, code), you must add the following reference to each slide:

© Alexander Amini and Ava Soleimany
MIT 6.S191: Introduction to Deep Learning
IntroToDeepLearning.com

If you are an MIT student, postdoc, faculty, or affiliate and would like to become involved with this course please email introtodeeplearning-staff@mit.edu. We are always accepting new applications to join the course staff.

This class would not be possible without our amazing sponsors and has been sponsored by Google, IBM, NVIDIA, Ernst and Young, LambdaLabs, Tencent AI, Microsoft, Amazon, and Onepanel. If you are interesting in becoming involved in this course as a sponsor please contact us at introtodeeplearning-staff@mit.edu.

To view archived versions of this website from past years please click here for 2021, 2020, 2019, 2018, and 2017.

6.S191 Team

amini

Alexander Amini

Lead Organizer
Instructor

asolei

Ava Soleimany

Lead Organizer
Instructor

Teaching Assistants

carmen

Carmen Martin Alonso

williamchen

William Chen

kristian

Kristian Georgiev

shinjini

Shinjini Ghosh

julia

Julia Moseyko

jacob

Jacob Phillips

rsander

Ryan Sander

sledzieski

Sam Sledzieski

gilbert

Gilbert Yang

We are always accepting new applications to join the course staff. If you are interested in becoming a TA, please contact introtodeeplearning-staff@mit.edu

Sponsors

This class and delivery would not be possible without our amazing sponsors! If you are interesting in becoming involved in this course as a sponsor please contact us at introtodeeplearning-staff@mit.edu