Verified project record

d2l-ai/d2l-en

An open-source interactive deep learning textbook written entirely in Jupyter notebooks that combines mathematical exposition, figures, and runnable code across multiple frameworks. It is freely accessible online and is used in university courses at 500 institutions across 70 countries, including Stanford, MIT, Harvard, and Cambridge.

Project overview

It unifies deep learning theory and practice in a single browsable resource by integrating exposition, math, and self-contained code in Jupyter notebooks, and it has documented university adoption at 500 institutions from 70 countries, including Stanford, MIT, Harvard, and Cambridge.

Project type: Model Development · Data Processing · Learning Resources
Use cases: Learning & Education
Deployment: Refer to project documentation
License: License pending

Best for

Educators seeking an interactive, unified open-source textbook to teach deep learning concepts, math, and multi-framework code to students.
Researchers and general users looking for a freely accessible online resource that integrates theory and runnable code for self-guided learning.

Key capabilities

Provides an open-source book drafted entirely in Jupyter notebooks that integrates figures, math, and interactive examples with self-contained code.
Offers sufficient technical depth and runnable code using multiple frameworks to solve problems in practice.

Limitations and risks

GPU requirements, minimum hardware, data boundary, and telemetry configurations are not documented.
The coding requirements needed to effectively use or run the Jupyter notebooks are not documented.

Getting started

The setup difficulty is documented as easy. Visit https://d2l.ai/ to browse the content; the book is freely accessible online without requiring local setup.

Alternatives and comparisons

Provides clear and concise examples covering TensorFlow v1 and v2 across basic models, neural networks, data management, and hardware to facilitate learning.
A suite of open-source Python modules, data sets, and tutorials supporting research and development in Natural Language Processing rather than general deep learning.
A standalone PyTorch beginner's guide and tutorial covering basic usage, advanced extensions, and practical applications with executable code and pretrained demo models.

Project comparisons

Evidence and sources

GitHub project description: Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
README: This open-source book represents our attempt to make deep learning approachable, teaching you the concepts, the context, and the code. The entire book is drafted in Jupyter notebo…
README: @book{zhang2023dive, title={Dive into Deep Learning}, author={Zhang, Aston and Lipton, Zachary C. and Li, Mu and Smola, Alexander J.}, publisher={Cambridge University Press}
Release: Release 1.0.3
README: Our goal is to offer a resource that could 1. be freely available for everyone;

Reviewed at: 2026-07-23T20:27:21Z

Open original GitHub project