MIT OpenCourseWare Courses

MIT Economist on AI, Trade-Offs and Healthcare

Explore economic principles with MIT's Jonathan Gruber as he discusses market failures, healthcare economics, and why "capitalism with gutter guards" ensures equitable outcomes.

• YouTube
• 29 minutes
• Self-Paced
• Free Video

PyTorch Tutorial - Introduction to Deep Learning Framework

Discover PyTorch fundamentals in this 29-minute tutorial covering the open-source deep learning framework's core concepts and practical applications for beginners.

• YouTube
• 29 minutes
• Self-Paced
• Free Video

Generative Models - Representation Learning Meets Generative Modeling - Lecture 15

Explore the intersection of representation learning and generative modeling through VAEs and latent variables in this MIT deep learning lecture.

• YouTube
• 1 hour 21 minutes
• Self-Paced
• Free Video

Scaling Laws in Neural Architectures - Lecture 20

Explore power laws in neural architectures, their theoretical foundations, limitations, and critical batch size concepts in deep learning systems.

• YouTube
• 38 minutes
• Self-Paced
• Free Video

Inference Methods for Deep Learning - Lecture 24

Explore advanced inference techniques beyond simple forward passes, including beam search, chain-of-thought reasoning, in-context learning, and test-time training methods.

• YouTube
• 1 hour 23 minutes
• Self-Paced
• Free Video

Introduction to Deep Learning - Lecture 1

Discover fundamental concepts and building blocks of deep neural networks in this comprehensive introduction to deep learning from MIT.

• YouTube
• 1 hour 1 minute
• Self-Paced
• Free Video

How to Train a Neural Network - Lecture 2

Master neural network training through stochastic gradient descent, backpropagation, and automatic differentiation in this MIT deep learning lecture.

• YouTube
• 1 hour 20 minutes
• Self-Paced
• Free Video

Representation Learning - Reconstruction-Based - Lecture 11

Explore reconstruction-based representation learning through autoencoders, clustering, vector quantization, and self-supervised methods with neural network insights.

• YouTube
• 1 hour 21 minutes
• Self-Paced
• Free Video

Generative Models - Conditional Models - Lecture 16

Explore conditional generative models including cGANs, cVAEs, and diffusion models for image-to-image, text-to-image, and cross-modal translation tasks.

• YouTube
• 1 hour 22 minutes
• Self-Paced
• Free Video

Architectures - Transformers - Lecture 8

Discover transformer architecture fundamentals through tokens, attention mechanisms, and positional encoding while exploring connections to MLPs, GNNs, and CNNs in this MIT deep learning lecture.

• YouTube
• 1 hour 15 minutes
• Self-Paced
• Free Video

Transfer Learning - Data - Lecture 19

Explore transfer learning techniques using generative models for data augmentation, domain adaptation, and advanced prompting methods in deep learning applications.

• YouTube
• 1 hour 16 minutes
• Self-Paced
• Free Video

Approximation Theory - Lecture 3

Explore how deep neural networks approximate functions through universal approximation theorems, Barron's theorem, and the role of depth in expressivity.

• YouTube
• 1 hour 23 minutes
• Self-Paced
• Free Video

Generalization - Out-of-Distribution (OOD) - Lecture 17

Explore out-of-distribution generalization challenges, including adversarial robustness and distribution shifts in deep learning models.

• YouTube
• 1 hour 5 minutes
• Self-Paced
• Free Video

Convolutional Neural Networks - Architectures for Grid Data - Lecture 4

Explore convolutional neural networks and their effectiveness for grid-based data structures in this MIT deep learning lecture.

• YouTube
• 1 hour 24 minutes
• Self-Paced
• Free Video

Representation Learning: Similarity-Based - Lecture 12

Explore similarity-based representation learning through metric learning, contrastive methods, InfoNCE loss, and alignment principles for effective deep learning applications.

• YouTube
• 1 hour 16 minutes
• Self-Paced
• Free Video