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 online virtually via MIT Canvas and publically open-sourced every week, starting March 9th, 2022.


Course Schedule

Lectures occured during MIT IAP 2022.
New lectures, slides, and labs will be open-sourced every week starting March 11 at 10AM ET!

Intro to Deep Learning
Lecture 1
Mar. 11, 2022

[Slides] [Video]

Deep Sequence Modeling
Lecture 2
Mar. 18, 2022

[Slides] [Video]

Intro to TensorFlow;
Music Generation
Software Lab 1

[Code]

Deep Computer Vision
Lecture 3
Mar. 25, 2022

[Slides] [Video]

Deep Generative Modeling
Lecture 4
Apr. 1, 2022

[Slides] [Video]

De-biasing Facial Recognition Systems
Software Lab 2

[Paper] [Code]

Deep Reinforcement Learning
Lecture 5
Apr. 8, 2022

[Slides] [Video]

Limitations and New Frontiers
Lecture 6
Apr. 15, 2022

[Slides] [Video]

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

[Code]

Autonomous Driving with LiDAR
Lecture 7
Apr. 22, 2022

[Info] [Video]

Speech Recognition
Lecture 10
Apr 29, 2022

[Info] [Video]

Final Project
Work on final projects

AI 4 Science
Lecture 9
May 13, 2022

[Info][Video]

Uncertainty in Deep Learning
Lecture 8
May 28, 2022

[Info] [Video]

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!
If you are an MIT student please register here. You can do this by clicking "create new form" and selecting "Add Drop". Enter the subject information (6.S191) and 6 units when prompted. You can also specify if you want to be registered as a listener or regular student 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

shinjini

Shinjini Ghosh

jody

Jody Mou

pushpita

Subha Pushpita

christa

Christabel Sitienei

sledzieski

Sam Sledzieski

nada

Nada Tarkhan

johnson

Tsun-Hsuan (Johnson) Wang

yudi

Yudi Xie

funing

Funing 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