Learn AIML - tinygrad prep

Policy note: this page includes only legal access routes: official free versions, open resources, publisher pages, and library/borrowing paths where available.

Best study order

Exact resources that are legally free

Free

Understanding Deep Learning — Simon J. D. Prince

Official site: https://udlbook.github.io/udlbook/
Main use: theory, backprop, neural networks, optimization.

Free

From Python to NumPy — Nicolas P. Rougier

Official online version: https://www.labri.fr/perso/nrougier/from-python-to-numpy/
Repository: https://github.com/rougier/from-python-to-numpy
Main use: arrays, vectorization, tensor thinking.

Free

Dive into Deep Learning

Official site: https://d2l.ai/
Main use: modern DL workflow and reference material.

Free

The Matrix Calculus You Need for Deep Learning

arXiv: https://arxiv.org/abs/1802.01528
Main use: matrix derivatives and gradient shape intuition.

Free

micrograd — Andrej Karpathy

Repository: https://github.com/karpathy/micrograd
Main use: autodiff and backprop in minimal code.

Free

tinygrad

Repository: https://github.com/tinygrad/tinygrad
Main use: the actual framework you want to understand and contribute to.

Exact resources available via borrowing / library access

Borrow

Grokking Deep Learning — Andrew Trask

Publisher page: https://www.manning.com/books/grokking-deep-learning
Search WorldCat / local libraries: https://search.worldcat.org/
Use your library / university access if available.

Borrow

Computer Systems: A Programmer's Perspective

Official page: https://csapp.cs.cmu.edu/
WorldCat: https://search.worldcat.org/

Borrow

Programming Massively Parallel Processors

Publisher page: https://www.elsevier.com/books/programming-massively-parallel-processors/kirk/978-0-323-91231-0
WorldCat: https://search.worldcat.org/

Exact resources that generally require purchase

Paid

Grokking Deep Learning — Andrew Trask

Publisher: https://www.manning.com/books/grokking-deep-learning
Worth it if you want a code-first implementation bridge.

Paid

Computer Systems: A Programmer's Perspective

Official site: https://csapp.cs.cmu.edu/
Later, for systems/performance depth.

Paid

Programming Massively Parallel Processors

Publisher: https://www.elsevier.com/books/programming-massively-parallel-processors/kirk/978-0-323-91231-0
Later, for GPU/backend/kernel work.

Learn AIML — tinygrad prep

Best study order

Exact resources that are legally free

Understanding Deep Learning — Simon J. D. Prince

From Python to NumPy — Nicolas P. Rougier

Dive into Deep Learning

The Matrix Calculus You Need for Deep Learning

micrograd — Andrej Karpathy

tinygrad

Exact resources available via borrowing / library access

Grokking Deep Learning — Andrew Trask

Computer Systems: A Programmer's Perspective

Programming Massively Parallel Processors

Exact resources that generally require purchase

Grokking Deep Learning — Andrew Trask

Computer Systems: A Programmer's Perspective

Programming Massively Parallel Processors

If you want a zero-cost path right now