No. 389 of 500 No. 36 in Deep Learning

Learning Deep Learning

Theory and Practice of Neural Networks, Computer Vision, Natural Language Processing, and Transformers Using TensorFlow

By Magnus Ekman

Published
August 17, 2021
Print length
752 pages
Reading level
Intermediate
ISBN-13
978-0137470358
Publisher
Addison-Wesley Professional
Written for
Developers and analysts with Python skills who want a structured, code-backed path into deep learning.

Synopsis

Magnus Ekman, a computer architect at NVIDIA, builds deep learning from first principles in the order it historically developed. The book opens with the Rosenblatt perceptron, then works through gradient-based learning, sigmoid neurons and backpropagation, and fully connected networks for classification and regression. A chapter on frameworks and network tweaks introduces the practical techniques that make deep networks trainable, before the book moves to convolutional networks for image classification, deeper pretrained models, and recurrent networks and LSTMs for time series and text autocompletion.

The language chapters are a particular strength. Ekman covers neural language models, word2vec and GloVe embeddings, sequence-to-sequence translation, and attention leading into the Transformer, then combines vision and language in an image-captioning network. A closing medley of topics and the appendices touch on later models, including GPT and BERT. Every concept is paired with code: the printed examples use TensorFlow with Keras, and matching PyTorch notebooks are available online. Readers finish with working implementations and a coherent mental model of why modern architectures are built as they are. The book was developed with the NVIDIA Deep Learning Institute and printed in full color.

Scorecard

Editorial score

How it scored

Editorial score: 65.3 / 1005 weighted criteria

  • Influence30%

    16.5/30
  • Authority25%

    17.5/25
  • Practical value20%

    15.0/20
  • Currency15%

    8.3/15
  • Readability10%

    8.0/10
  • Editorial score

    65.3/100

How the rank was computed

Rank No. 389 of 500 comes from a composite of 50.1: observable signals 20.7 of 55 points plus editorial review 29.4 of 45 points.

All 11 inputs
InputPoints
Observable signals20.7/55
Reach (Amazon ratings volume)7.9/16.5
Consensus across best-of lists5.5/13.8
Awards and bestseller evidence0.0/8.3
Reader rating, sample-adjusted6.9/8.3
Amazon sales rank0.4/5.5
Recency0.0/2.8
Editorial review29.4/45
Author authority7.9/11.3
Influence7.4/13.5
Practical value6.8/9.0
Readability3.6/4.5
Currency3.7/6.8

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

A thorough, well-sequenced deep learning course from perceptrons to transformers, held back mainly by its TensorFlow-first code.

Strengths

  • Logical progression from perceptron to Transformer
  • Strong natural language processing coverage
  • Free PyTorch notebooks complement TensorFlow text

Keep in mind

Printed code uses TensorFlow while most researchers now favor PyTorch, and the 2021 text predates instruction-tuned LLMs and modern generative AI practice.

Key takeaways

  1. Understanding the single perceptron and gradient descent thoroughly makes every later architecture, from CNNs to transformers, easier to reason about.
  2. Practical tweaks such as better activation functions, initialization, normalization and regularization are what make deep networks train reliably.
  3. Word embeddings such as word2vec and GloVe turn text into geometry, giving networks a meaningful numeric representation of language.
  4. Attention lets a model weigh every input position directly, which is why the Transformer displaced recurrent networks for language tasks.

Notable facts

  • Developed in partnership with the NVIDIA Deep Learning Institute; the material is also offered as a video course, Learning Deep Learning: From Perceptron to Large Language Models. Source (opens in a new tab)

About the author

Magnus Ekman

Magnus Ekman, PhD, is a director of architecture at NVIDIA, where he has led engineering work on CPU performance and power efficiency for systems-on-chip. He holds a doctorate in computer engineering and multiple patents, previously worked on processor design at Sun Microsystems and Samsung Research America, and helped start two companies, including Skout. He partnered with the NVIDIA Deep Learning Institute on this book.

Questions

What is Learning Deep Learning about?
It is a step-by-step course in deep learning that starts with the perceptron and backpropagation and progresses through convolutional networks for images, recurrent networks and LSTMs for sequences, word embeddings, sequence-to-sequence translation, attention and the Transformer, and image captioning. Each chapter pairs explanation with TensorFlow code, and PyTorch versions of the examples are available online.
Who should read Learning Deep Learning?
It suits software developers, data analysts and students who can program in Python and want a ground-up understanding of neural networks. The publisher pitches it at readers without prior machine learning or statistics experience, though comfort with basic algebra helps. Researchers seeking cutting-edge methods, or practitioners who only need skills for building applications on large language models, should look elsewhere.
Is Learning Deep Learning still useful in 2026?
For fundamentals, yes. Its explanations of backpropagation, convolution, recurrence, embeddings and attention remain accurate, and the online PyTorch notebooks ease the TensorFlow issue. It was published in 2021, however, so it does not cover instruction tuning, retrieval-augmented generation, agents or other techniques that now define applied work with large language models.

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.