A List of Open Courses in Deep Learning

Here is a categorized list of courses and resources for learning about deep learning and related fields.

Foundations (Optimization & Math)

• The Iris Book (Matrix Power) (Note: This is likely a reference to a foundational text, possibly “Dive into Deep Learning” or another book focusing on the underlying mathematics like matrix calculus.)
• CMU 10-725: Convex Optimization
• Stanford CS109: Probability for Computer Scientists
• UCB EECS 126: Probability and Random Processes

Deep Learning (General & Introductory)

• Dive into Deep Learning (Note: This is the official English name for “动手学习深度学习”)
• MIT 6.S191: Intro to Deep Learning
• Stanford CS229: Machine Learning
• Stanford CS 230: Deep Learning
• UCB CS 182: Deep Neural Networks

Deep Learning (Advanced Topics)

• MIT 6.S898/6.7960: Deep Learning
• Stanford CS 330: Deep Multi-Task and Meta Learning
• Stanford CS329D: ML Under Distribution Shifts

Reinforcement Learning

• MIT 6.7920: Reinforcement Learning: Foundations And Methods (Fall 2024)
• Hands-on Reinforcement Learning (Note: Assumed to be a reference to a hands-on course/book like this one)
• UCB CS 285: Deep Reinforcement Learning
• UCB Deep RL BootCamp
• OpenAI Spinning up Reinforcement Learning
• U Toronto STA 4273: Minimizing Expectations (Reinforcement Learning) (Winter 2021)

Natural Language Processing & Large Language Models

• Stanford CS336: Language Modeling from Scratch
• CMU 11-667: Large Language Models: Methods and Applications
• MIT 6.S986: Large Language Models and Beyond
• Stanford CS 324: Large language models
• Stanford CS224N: Natural Language Processing with Deep Learning
• Stanford CS25: Transformers United V2

Computer Vision

• MIT 6.8300/6.8301: Advances in Computer Vision
• Stanford CS 231N: Deep Learning for Computer Vision

Generative Models

• MIT 6.S978: Deep Generative Models
• Stanford CS 236G: Generative Adversarial Networks (GANs)
• Stanford CS 236: Deep Generative Models
• Columbia STAT 8201: Deep Generative Models (GAN)

ML Systems, Data Engineering & Hardware

• MIT 6.5930/1: Hardware Architecture for Deep Learning
• MIT 6.S079: Software Systems for Data Science
• MIT 6.S984: Datacenter Computing
• CMU 10-714: Deep Learning Systems
• Stanford CS246: Mining Massive Data Sets (by Jure Leskovec)
• Stanford CS 329S: Machine Learning Systems Design

Edge Computing & Efficient ML

• MIT 6.S965: TinyML and Efficient Deep Learning Computing

Graph Neural Networks & Graph ML

• Stanford CS224W: Machine Learning with Graphs (by Jure Leskovec)

Data Science & Visualization

• MIT 6.859: Interactive Data Visualization
• Stanford CS 448B: Visualization

Robotics & Embodied AI

• MIT 6.S953: Embodied Intelligence

AI Ethics & Society

• Stanford: Ethics of Artificial Intelligence (Fairness & Differential privacy & Federated Learning)

Computer Science Fundamentals

• Stanford CS45: Software Tools Every Programmer Should Know