Subjects / Deep learning

Best books to learn Deep learning, in order

Deep learning has a real prerequisite chain most tutorials paper over. Intuition and hands-on practice come first, but the math — linear algebra, calculus, probability — is what makes backpropagation and training actually click rather than stay a black box. Then come the architectures: CNNs, RNNs, transformers, in that historical order. Applied first, then the theory that explains why it works, then the models.

Build your own Deep learning list →Browse all paths

Reading paths for deep learning

Popular deep learning books

Related reading

Frequently asked questions

How should I approach learning deep learning?
Deep learning has a real prerequisite chain most tutorials paper over. Intuition and hands-on practice come first, but the math — linear algebra, calculus, probability — is what makes backpropagation and training actually click rather than stay a black box. Then come the architectures: CNNs, RNNs, transformers, in that historical order. Applied first, then the theory that explains why it works, then the models.
What's a good book to start deep learning with?
A strong starting point is Neural Networks and Deep Learning by Michael A. Nielsen. The ordered reading paths above show exactly where it fits and what to read next.
What should I read after deep learning?
Once you have the fundamentals, explore closely related subjects like Ethical hacking & penetration testing, Computer networking, Docker & Kubernetes.

Related subjects