Home
Explore Uedu
Student Console
Register as Member/Login
Research Informed Consent Center
Survey Center
Educational Big Data Challenge
UeduGPTs
Aida Learning Companion
Agentic AI
Local AI
Uedu Code
Find an Advisor
Paper Reading
Uedu Note
Uedu Open
Uedu Jupyter
Language Learning
Lingua Writing
My Writing History
Cognomics Test Toolkit
Uedu Finance
Uedu Interdisciplinary General Education
Uedu Physics
Uedu Calculus
Uedu Biology
Uedu Chemistry
Uedu Electronics
Uedu Semiconductor
Uedu AI
Uedu Statistics
Uedu UAV
Teaching Materials
Literature Hall
Taiwan: Four Hundred Years
Uedu Science
Course settings
Try a Scenario Task
Support & Messages
Uptime Data

UeduGPTs

--

Jupyters

1

Local AI

--

Uedu Code

--

CISOSE26 Local AI Uedu Code UG26
Taipei AQI 56 · Taichung AQI 60 · Tainan AQI 86 · Kaohsiung AQI 63
AI Reply Desktop Notifications

Show a desktop notification when the AI TA finishes replying

Chat Message Notifications

Notify me when classmates post messages in the forum

Sound notification

Play an alert sound whenever there is a new notification

More settings
Account settings Data privacy settings Research Informed Consent Form
Uedu Open / Deep Learning
6.7960

Deep Learning

Prof. Phillip Isola, Prof. Sara Beery, Dr. Jeremy Bernstein | Fall 2024
Data Science, Analytics & Computer Technology AI Machine Learning Visualization Computer Science Engineering Artificial Intelligence Graphics and Visualization
Go to original course
CC BY-NC-SA 4.0
Course introduction
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.
Course Information
SourceMIT 開放式課程
DepartmentElectrical Engineering and Computer Science
LanguageEnglish
Number of videos24
Course videos (24)
1
Lec 01. Introduction to Deep Learning
Lec 01. Introduction to Deep Learning
2
Lec 02. How to Train a Neural Net
Lec 02. How to Train a Neural Net
3
Lec 03. Approximation Theory
Lec 03. Approximation Theory
4
Lec 04. Architectures: Grids
Lec 04. Architectures: Grids
5
Lec 05. Architectures: Graphs
Lec 05. Architectures: Graphs
6
Lec 06. Generalization Theory
Lec 06. Generalization Theory
7
Lec 07. Scaling Rules for Optimization
Lec 07. Scaling Rules for Optimization
8
Lec 08. Architectures: Transformers
Lec 08. Architectures: Transformers
9
Lec 09. Hacker's Guide to Deep Learning
Lec 09. Hacker's Guide to Deep Learning
10
Lec 10. Architectures: Memory
Lec 10. Architectures: Memory
11
Lec 11. Representation Learning: Reconstruction-Based
Lec 11. Representation Learning: Reconstruction-Based
12
Lec 12. Representation Learning: Similarity-Based
Lec 12. Representation Learning: Similarity-Based
13
Lec 13. Representation Learning: Theory
Lec 13. Representation Learning: Theory
14
Lec 14. Generative Models: Basics
Lec 14. Generative Models: Basics
15
Lec 15. Generative Models: Representation Learning Meets Generative Modeling
Lec 15. Generative Models: Representation Learning Meets Generative Modeling
16
Lec 16. Generative Models: Conditional Models
Lec 16. Generative Models: Conditional Models
17
Lec 17. Generalization: Out-of-Distribution (OOD)
Lec 17. Generalization: Out-of-Distribution (OOD)
18
Lec 18. Transfer Learning: Models
Lec 18. Transfer Learning: Models
19
Lec 19. Transfer Learning: Data
Lec 19. Transfer Learning: Data
20
Lec 20. Scaling Laws
Lec 20. Scaling Laws
21
Lec 21. Language Models
Lec 21. Language Models
22
Lec 23. Metrized Deep Learning
Lec 23. Metrized Deep Learning
23
Lec 24. Inference Methods for Deep Learning
Lec 24. Inference Methods for Deep Learning
24
PyTorch Tutorial
PyTorch Tutorial