Back to index
OtherSelf paced open book, roughly a full semester of material if you work through it seriously·Completely free online, with an optional printed edition from Cambridge University Press

Dive into Deep Learning (D2L.ai)

4.7

The single best free resource I know of for people who want both the maths and the code to sit side by side. Dive into Deep Learning is a proper textbook you can run, edit and experiment with, and the fact that it costs nothing still surprises me given the quality.

What We Liked

  • Every chapter mixes clear explanation, real maths and runnable notebooks, so you never have to guess how a formula becomes code
  • Available in PyTorch, TensorFlow, JAX and more, so you learn in the framework you actually use
  • Written and maintained by working researchers, and adopted as a course text at hundreds of universities
  • Genuinely free and open source, with an active forum and regular updates as the field moves

What Could Be Better

  • It is a serious book, not a gentle weekend course, and the maths chapters will humble you if you rush them
  • There is no instructor, video or cohort, so all the accountability has to come from you
  • The breadth means some newer topics get lighter treatment than the classic architectures
  • Working through it properly is a real time commitment that many people underestimate

Detailed review

Dive into Deep Learning, usually shortened to D2L, is the rare free resource that I would still recommend even if it cost money. It is an open source book built around Jupyter notebooks, so instead of reading about a concept and then hunting for an implementation somewhere else, you get the explanation, the maths and the working code in one continuous flow, and you can run and change any of it as you read. The authors come from Amazon and the wider research community, and the care shows, because the writing manages to be rigorous without turning into a wall of notation that only a graduate student could follow. What really sets it apart is the multi framework support.

The same content is available in PyTorch, TensorFlow and JAX, which means you are not forced to learn in a stack you will never touch again, and that alone has made it a default text in hundreds of university courses. The coverage runs from linear regression and the basics of neural networks through convolutional and recurrent architectures, attention and transformers, and on to optimisation and the practical realities of training. My honest reservation is simply that this is a book, and a demanding one, so nobody is going to hold your hand. There is no video lecturer, no cohort and no deadline, and the mathematical sections in particular will expose any gaps you have been avoiding.

That is a feature for serious learners and a wall for casual ones. I would also say that because it tries to cover so much, a few of the most current topics are treated more briefly than the well established material, so it is a foundation rather than a bleeding edge survey. But as a way to actually understand deep learning, with the theory and the implementation locked together, I have not found a free resource that beats it. Work through it like a proper course, do the exercises, and modify the notebooks rather than just running them, and you will come out with the kind of grounded understanding that transfers to whatever you build next.

[ final ]

The verdict.

If you can supply the discipline, this is close to the perfect self study text for deep learning, and it is free. I would happily point a motivated learner here over most paid courses covering the same ground. Just treat it like a university module, not a quick read, and actually run and modify the code rather than skimming it.