#5555th of 55 in Learning and cookbooks
introtodeeplearning
Jupyter notebook labs for MIT's Introduction to Deep Learning course
- Stars
- 8.8k
- License
- MIT
- Last commit
- Jan 2026
- Last release
- Jan 2025
- Language
- Jupyter Notebook
8,508 on 1 Apr 20268,847 on 21 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Code and software labs (lab1, lab2, lab3) for the MIT Introduction to Deep Learning course, written as Jupyter notebooks with #TODO cells to fill in. They run in Google Colab with a GPU runtime and use the companion `mitdeeplearning` pip package for helper functions. Lecture slides and videos are hosted on the course website and YouTube.
Who it is for: Students learning deep learning through hands-on notebook labs
Strengths
- Self-paced labs with #TODO cells to complete, tied to public lecture videos
- Runs in Google Colab, so no local install or local GPU is needed
- Helper package `mitdeeplearning` is on PyPI and reusable outside the course
- Code is MIT licensed
Weaknesses
- Requires a Google account to run the labs in Colab
- Only three labs; covers course material, not a general cookbook
- Reuse of code and slides must carry the MIT Introduction to Deep Learning attribution
- Last release is 2025-01-08, older than the 2026 lab update
What it needs
- GPU optional
- Needs Google Colab, Google account, mitdeeplearning (pip)
Also in Learning and cookbooks
See all 55| Rank | Project | Score |
|---|---|---|
| 1 | ai-engineering-from-scratchHands-on AI engineering curriculum with 542 lessons across 20 phases | 90 out of 100 |
| 2 | generative-ai-for-beginners21-lesson course on building generative AI apps in Python and TypeScript | 81 out of 100 |
| 3 | ai-agents-for-beginners18-lesson course on building AI agents with Microsoft Agent Framework | 79 out of 100 |
| #4 | cs249r_bookOpen textbook and course materials for machine learning systems engineering | 79 out of 100 |
| #5 | llms-from-scratchCode for the book on building a GPT-style LLM in PyTorch | 77 out of 100 |