Hands-on Deep Learning

Hands-on Deep Learning is an open-source, interactive Chinese-language textbook on deep learning that blends code, mathematics, and discussion to help readers systematically master deep learning theory and practice from scratch.

Visit Website

Deep Learning TextbookHands-on Deep Learning TutorialPyTorch Deep Learning TutorialsOpen-source Chinese Deep Learning BookLi Mu's Deep Learning CourseIntroduction to Practical Deep Learning

Features of Hands-on Deep Learning

Provides runnable code in multiple frameworks such as PyTorch and TensorFlow, ensuring a tight integration of theory and practice
Uses an interactive Jupyter Notebook learning approach, supporting online code editing and instant results
Covers models from linear regression to cutting-edge models like Transformers; comprehensive and continually updated
Accompanied by Li Mu's teaching videos and online courses, forming a holistic learning ecosystem
Has been adopted by nearly 500 universities worldwide, and its content quality and instructional practicality are widely recognized

Use Cases of Hands-on Deep Learning

Faculty and students in computer-related majors at universities, using it as the core textbook or reference for deep learning courses
Engineers or developers looking to transition into the AI field, using it for systematic self-study of core deep learning techniques
Data science practitioners or researchers who need quick access to model implementation code or theoretical explanations
Participants in Kaggle or other data science competitions, using it to learn practical techniques and model-building methods
Individual learners can practice code hands-on through its online interactive environment without configuring a local setup

FAQ about Hands-on Deep Learning

What is Hands-on Deep Learning? Who is it suitable for?

It is an open-source, interactive Chinese-language deep learning textbook suitable for computer science students, AI-transitioning engineers, researchers, and others who want to systematically learn deep learning theory and practice.

What background is needed to study Hands-on Deep Learning?

A basic knowledge of Python programming is recommended. The book starts from mathematical basics, and beginners can study in order, acquiring the necessary mathematics and framework knowledge through practice.

Which deep learning frameworks' code does Hands-on Deep Learning provide?

The second edition mainly provides implementation code for several mainstream frameworks, including PyTorch, TensorFlow, NumPy/MXNet, PaddlePaddle, and JAX, to facilitate user choice.

Is there a printed version of Hands-on Deep Learning? How does it differ from the online version?

Yes. The second edition, Hands-on Deep Learning (PyTorch Edition), is available in print on JD.com and Dangdang; the content is broadly similar to the online version, convenient for offline reading.

How to get the latest updates of Hands-on Deep Learning?

All content is open-source on GitHub; it is recommended to follow its GitHub repository to obtain the latest code and chapter updates.

Where can I watch Li Mu's courses that accompany Hands-on Deep Learning?

The PyTorch version of the instructional videos can be viewed on Bilibili, and the course livestream recordings are also provided there, synchronized with the textbook content.

Features of Hands-on Deep Learning

Provides runnable code in multiple frameworks such as PyTorch and TensorFlow, ensuring a tight integration of theory and practice

Uses an interactive Jupyter Notebook learning approach, supporting online code editing and instant results

Covers models from linear regression to cutting-edge models like Transformers; comprehensive and continually updated

Accompanied by Li Mu's teaching videos and online courses, forming a holistic learning ecosystem

Has been adopted by nearly 500 universities worldwide, and its content quality and instructional practicality are widely recognized

Use Cases of Hands-on Deep Learning

Faculty and students in computer-related majors at universities, using it as the core textbook or reference for deep learning courses

Engineers or developers looking to transition into the AI field, using it for systematic self-study of core deep learning techniques

Data science practitioners or researchers who need quick access to model implementation code or theoretical explanations

Participants in Kaggle or other data science competitions, using it to learn practical techniques and model-building methods

Individual learners can practice code hands-on through its online interactive environment without configuring a local setup

FAQ about Hands-on Deep Learning

What is Hands-on Deep Learning? Who is it suitable for?

What background is needed to study Hands-on Deep Learning?

Which deep learning frameworks' code does Hands-on Deep Learning provide?

The second edition mainly provides implementation code for several mainstream frameworks, including PyTorch, TensorFlow, NumPy/MXNet, PaddlePaddle, and JAX, to facilitate user choice.

Is there a printed version of Hands-on Deep Learning? How does it differ from the online version?

Yes. The second edition, Hands-on Deep Learning (PyTorch Edition), is available in print on JD.com and Dangdang; the content is broadly similar to the online version, convenient for offline reading.

How to get the latest updates of Hands-on Deep Learning?

All content is open-source on GitHub; it is recommended to follow its GitHub repository to obtain the latest code and chapter updates.

Where can I watch Li Mu's courses that accompany Hands-on Deep Learning?

The PyTorch version of the instructional videos can be viewed on Bilibili, and the course livestream recordings are also provided there, synchronized with the textbook content.