No. 154 of 500 No. 14 in Deep Learning

Understanding Deep Learning

By Simon J. D. Prince

Print length
544 pages
Publisher
The MIT Press
Reading level
Advanced
ISBN-13
978-0262048644
Published
December 5, 2023
Written for
Students, engineers and researchers with applied math background who want a rigorous grasp of modern deep learning.

Synopsis

Simon Prince's Understanding Deep Learning sets out to teach the ideas behind modern neural networks without burying them in detail. Each concept is explained first in plain language, then stated precisely in mathematical notation and illustrated with carefully designed figures. The book starts with supervised learning and shallow networks, reaching neural networks after only a few pages of setup, then works through deep networks, loss functions, model fitting, gradients and initialization, performance measurement and regularization. Prince deliberately cut topics he judged nonessential, including recurrent networks, to keep the core compact.

The second half covers the architectures and generative models that define current practice: convolutional and residual networks, transformers, graph neural networks, generative adversarial networks, normalizing flows, variational autoencoders and diffusion models, followed by deep reinforcement learning and a chapter on why deep networks work as well as they do. A closing chapter on ethics, co-written with philosopher Travis LaCroix, addresses bias, explainability and social effects. A free online edition and Python notebooks let readers test each idea in code. Readers who finish the book understand how systems such as large language models and image generators work and can implement simple versions of them.

Scorecard

Editorial score

How it scored

Editorial score: 80.8 / 1005 weighted criteria

  • Influence30%

    24.0/30
  • Authority25%

    21.3/25
  • Practical value20%

    15.0/20
  • Currency15%

    12.0/15
  • Readability10%

    8.5/10
  • Editorial score

    80.8/100

How the rank was computed

Rank No. 154 of 500 comes from a composite of 59.2: observable signals 22.8 of 55 points plus editorial review 36.4 of 45 points.

All 11 inputs
InputPoints
Observable signals22.8/55
Reach (Amazon ratings volume)8.6/16.5
Consensus across best-of lists2.8/13.8
Awards and bestseller evidence0.0/8.3
Reader rating, sample-adjusted8.2/8.3
Amazon sales rank1.5/5.5
Recency1.7/2.8
Editorial review36.4/45
Author authority9.6/11.3
Influence10.8/13.5
Practical value6.8/9.0
Readability3.8/4.5
Currency5.4/6.8

Each criterion is scored from 1 to 10 and weighted, and the points add up to the editorial score. The rank combines observable signals (55 percent) with this score (45 percent). Read the methodology.

Verdict

One of the clearest modern deep learning textbooks, pairing precise mathematics with visual intuition from basics through transformers and diffusion models.

Strengths

  • Exceptional figures that clarify difficult concepts
  • Covers transformers and diffusion models in depth
  • Free online edition with companion Python notebooks

Keep in mind

Readers need comfort with calculus, linear algebra and probability, and the book favors conceptual understanding over framework-specific engineering or LLM deployment practice.

Key takeaways

  1. Networks with ReLU activations compute piecewise-linear functions, and depth lets them create far more linear regions per parameter than shallow networks.
  2. Training success depends as much on initialization, loss design, optimizer choice and regularization as on the choice of network architecture.
  3. Self-attention, residual connections and normalization are the architectural ideas that made today's large language models trainable at scale.
  4. GANs, normalizing flows, variational autoencoders and diffusion models are different strategies for one task: modeling the probability distribution behind the data.

Notable facts

  • The book's GitHub repository, which hosts its notebooks, slides and figures, has more than 10,000 stars. Source (opens in a new tab)
  • The University of North Texas deep learning course CSCE 5218 assigns it as the required textbook for Spring 2026. Source (opens in a new tab)
  • Prince left RBC Borealis in 2021 to write the book, which The MIT Press released on December 5, 2023. Source (opens in a new tab)

About the author

Simon J. D. Prince

Simon J. D. Prince is an honorary professor of computer science at the University of Bath and the author of Computer Vision: Models, Learning and Inference. He has led research teams in academia and industry, including at Anthropics Technologies and at RBC Borealis in Montreal, where he was a research director from 2019 to 2021 before leaving to write this book.

Questions

Is Understanding Deep Learning good for beginners?
It is accessible to newcomers to deep learning but not to newcomers to mathematics. Readers should be comfortable with calculus, linear algebra and basic probability. Prince explains each idea in plain language before formalizing it and relies heavily on figures, so students who meet those prerequisites often find it easier to follow than older deep learning textbooks.
Is Understanding Deep Learning free?
A free online edition is available from the book's website, udlbook.com, along with Python notebooks, slides and figures, and the companion GitHub repository is published under a Creative Commons noncommercial license. The MIT Press sells the printed hardcover. The free edition makes the book practical for self-study and for university courses, such as North Texas's CSCE 5218, which assigns it as required reading.
Does Understanding Deep Learning cover transformers and large language models?
Yes. It devotes a full chapter to transformers, explaining self-attention, positional encoding and the encoder and decoder designs behind models such as BERT and GPT, and it also covers the diffusion models used in image generation. Because it appeared in late 2023, it does not treat later developments such as reasoning models or current alignment and fine-tuning practice in depth.

Sources

As an Amazon Associate, Best AI Books earns from qualifying purchases. Best AI Books is sponsored by Iternal.ai, whose founder and CEO, John Byron Hanby IV, wrote The AI Strategy Blueprint, our #1 ranked book. How we rank books.