Introduction to Deep Learning
1:00:51How to Train a Neural Net
1:19:34Approximation Theory
1:22:42Architectures: Grids
1:23:57Architectures: Graphs
1:21:14Generalization Theory
1:20:31Scaling Rules for Optimization
1:20:56Architectures: Transformers
1:14:35Hacker's Guide to Deep Learning
1:15:51Architectures: Memory
1:13:28Representation Learning: Reconstruction-Based
1:21:04Representation Learning: Similarity-Based
1:16:20Representation Learning: Theory
1:15:21Generative Models: Basics
1:21:18Generative Models: Representation Learning Meets Generative Modeling
1:20:40Generative Models: Conditional Models
1:21:32Generalization: Out-of-Distribution (OOD)
1:04:41Transfer Learning: Models
1:25:42Transfer Learning: Data
1:15:44Scaling Laws
38:23Generalization: Out-of-Distribution (OOD)
This video investigates out-of-distribution (OOD) generalization challenges, including adversarial robustness and managing distribution shifts. It provides strategies for improving model performance in novel environments.
MIT 6.7960 Deep Learning, Fall 2024
Generative Models: Conditional Models
Next · Lecture 18Transfer Learning: Models