Lecture 01: Introduction to Deep Learning (6.7960)
1:00:51Lecture 02: How to Train a Neural Net (6.7960)
1:19:34Lecture 03: Approximation Theory (6.7960)
1:22:42Lecture 04: Architectures: Grids (6.7960)
1:23:57Lecture 05: Architectures: Graphs (6.7960)
1:21:14Lecture 06: Generalization Theory (6.7960)
1:20:31Lecture 07: Scaling Rules for Optimization (6.7960)
1:20:56Lecture 08: Architectures: Transformers (6.7960)
1:14:35Lecture 09: Hacker's Guide to Deep Learning (6.7960)
1:15:51Lecture 10: Architectures: Memory (6.7960)
1:13:28Lecture 11: Representation Learning: Reconstruction-Based (6.7960)
1:21:04Lecture 12: Representation Learning: Similarity-Based (6.7960)
1:16:20Lecture 13: Representation Learning: Theory (6.7960)
1:15:21Lecture 14: Generative Models: Basics (6.7960)
1:21:18Lecture 15: Generative Models: Representation Learning Meets Generative Modeling (6.7960)
1:20:40Lecture 16: Generative Models: Conditional Models (6.7960)
1:21:32Lecture 17: Generalization: Out-of-Distribution (OOD) (6.7960)
1:04:41Lecture 18: Transfer Learning: Models (6.7960)
1:25:42Lecture 19: Transfer Learning: Data (6.7960)
1:15:44Lecture 20: Scaling Laws (6.7960)
38:23Lecture 14: Generative Models: Basics (6.7960)
This lecture introduces foundational generative models, including density and energy models, sampling techniques, GANs, autoregressive models, and diffusion models. It provides a broad overview of their mechanisms.
MIT 6.7960 Deep Learning, Fall 2024
Instructor: Phillip Isola
View the complete course: https://ocw.mit.edu/courses/6-7960-deep-learning-fall-2024/
YouTube Playlist: https://www.youtube.com/playlist?list=PLUl4u3cNGP63URZnh5iqBzDTDYPUTQT-8
Lecture 13: Representation Learning: Theory (6.7960)
Next · Lecture 15Lecture 15: Generative Models: Representation Learning Meets Generative Modeling (6.7960)
Seminar notes & discussion
No public seminar notes on this lecture yet.