Learn · MIT OpenCourseWare

Visual prompt-based in-painting model performing tasks like segmentation, colorization, in-painting, and style transfer.

Course6.796024 lectures

Deep Learning

Prof. Phillip Isola, Prof. Sara Beery and Dr. Jeremy Bernstein · Massachusetts Institute of Technology

Start with lecture 1 At MIT OpenCourseWare

About

This course covers the fundamentals of deep learning, including both theory and applications. Topics include neural net architectures (MLPs, CNNs, RNNs, graph nets, transformers), geometry and invariances in deep learning, backpropagation and automatic differentiation, learning theory and generalization in high dimensions, and applications to computer vision, natural language processing, and robotics.

This course is supported for the 2026-2027 academic year in part by:

Dr. Michael Borowitz SB ’71

Steven R. Weiss SB ‘66

Lectures

Lecture Videos

  1. Lec 01. Introduction to Deep Learning Video
  2. Lec 02. How to Train a Neural Net Video
  3. Lec 03. Approximation Theory Video
  4. Lec 04. Architectures: Grids Video
  5. Lec 05. Architectures: Graphs Video
  6. Lec 06. Generalization Theory Video
  7. Lec 07. Scaling Rules for Optimization Video
  8. Lec 08. Architectures: Transformers Video
  9. Lec 09. Hacker's Guide to Deep Learning Video
  10. Lec 10. Architectures: Memory Video
  11. Lec 11. Representation Learning: Reconstruction-Based Video
  12. Lec 12. Representation Learning: Similarity-Based Video
  13. Lec 13. Representation Learning: Theory Video
  14. Lec 14. Generative Models: Basics Video
  15. Lec 15. Generative Models: Representation Learning Meets Generative Modeling Video
  16. Lec 16. Generative Models: Conditional Models Video
  17. Lec 17. Generalization: Out-of-Distribution (OOD) Video
  18. Lec 18. Transfer Learning: Models Video
  19. Lec 19. Transfer Learning: Data Video
  20. Lec 20. Scaling Laws Video
  21. Lec 21. Language Models Video
  22. Lec 23. Metrized Deep Learning Video
  23. Lec 24. Inference Methods for Deep Learning Video
  24. PyTorch Tutorial Video

Syllabus and materials

At MIT OpenCourseWare, as the course publishes them.

Credits and licence

Institution
Massachusetts Institute of Technology
Department
Electrical Engineering and Computer Science
Taught by
Prof. Phillip Isola, Prof. Sara Beery, Dr. Jeremy Bernstein
Term
Fall 2024
Level
Undergraduate
Language
English
Subjects
Computer science, Engineering
Source
MIT OpenCourseWare
Licence
CC BY 4.0, as MIT OpenCourseWare states it. MIT OpenCourseWare's terms
Attribution
Prof. Phillip Isola, Prof. Sara Beery, Dr. Jeremy Bernstein. Deep Learning. Fall 2024. Massachusetts Institute of Technology: MIT OpenCourseWare, https://ocw.mit.edu/. License: Creative Commons BY-NC-SA.
Who can watch
MIT OpenCourseWare gives no rating. Invisible Network shows it to Tweens profiles and older, judged from what the source says about it. How courses are placed