No. 405 of 500 No. 66 in Hands-On AI & Programming

AI and Machine Learning for Coders

A Programmer's Guide to Artificial Intelligence

By Laurence Moroney

Print length
390 pages
Publisher
O'Reilly Media
Reading level
Intermediate
ISBN-13
978-1492078197
Published
November 10, 2020
Written for
Python-literate software developers taking their first practical steps into building and deploying neural networks.

Synopsis

Laurence Moroney, who spent a decade as Google's AI advocacy lead and developed the TensorFlow Developer Professional Certificate courses on Coursera from the same material, wrote this book for software developers who want to build machine learning models without first wading through advanced mathematics. He starts with a single neuron learning a simple linear relationship, then builds up to convolutional networks for computer vision, explaining filters and pooling in code rather than equations. Later chapters cover natural language processing, from tokenizing text and creating embeddings to recurrent networks and text generation, and sequence models for time-series prediction, all in Python with TensorFlow and Keras.

The second half turns to deployment, which Moroney treats as TensorFlow's distinguishing strength. Readers convert models with TensorFlow Lite and run them in Android and iOS apps, use TensorFlow.js for inference and transfer learning in the browser, serve models over REST and gRPC with TensorFlow Serving, and get an introduction to federated learning. A closing chapter addresses AI ethics, fairness and privacy. The result is a practical map of the full path from training a model to shipping it inside an application, though PyTorch has since overtaken TensorFlow in much of the field and the book predates large language models.

Scorecard

Editorial score

How it scored

Editorial score: 68.6 / 1005 weighted criteria

  • Influence30%

    21.0/30
  • Authority25%

    18.8/25
  • Practical value20%

    14.0/20
  • Currency15%

    6.8/15
  • Readability10%

    8.0/10
  • Editorial score

    68.6/100

How the rank was computed

Rank No. 405 of 500 comes from a composite of 49.7: observable signals 18.9 of 55 points plus editorial review 30.8 of 45 points.

All 11 inputs
InputPoints
Observable signals18.9/55
Reach (Amazon ratings volume)8.9/16.5
Consensus across best-of lists2.8/13.8
Awards and bestseller evidence0.0/8.3
Reader rating, sample-adjusted6.5/8.3
Amazon sales rank0.7/5.5
Recency0.0/2.8
Editorial review30.8/45
Author authority8.4/11.3
Influence9.5/13.5
Practical value6.3/9.0
Readability3.6/4.5
Currency3.0/6.8

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 clear, code-first TensorFlow introduction for programmers, still useful for fundamentals though its framework and deployment tooling have aged.

Strengths

  • Code-first explanations with minimal math
  • Covers mobile, browser and server deployment
  • Pairs with Moroney's Coursera TensorFlow certificate courses

Keep in mind

Built on TensorFlow and Keras APIs from 2020; readers working in PyTorch or with large language models will need newer resources.

Key takeaways

  1. Machine learning inverts traditional programming: instead of writing rules, developers supply data and answers and let a model infer the rules.
  2. Convolutions and pooling let a network learn visual features such as edges and shapes, making image classification feasible with modest code.
  3. Text must be tokenized, sequenced and embedded before a neural network can learn from it, and recurrent layers help capture word order.
  4. A model delivers value only once deployed, so plan early for mobile, browser or server runtimes such as TensorFlow Lite, TensorFlow.js and Serving.

Notable facts

  • Moroney has said the book and the TensorFlow Developer Professional Certificate on Coursera were developed from the same material and are complementary. Source (opens in a new tab)
  • O'Reilly published Moroney's follow-up, AI and ML for Coders in PyTorch, in July 2025, adding generative AI with Hugging Face Diffusers and Transformers. Source (opens in a new tab)

About the author

Laurence Moroney

Laurence Moroney leads AI at Arm and is an AI Fund Fellow. He spent ten years at Google as AI Advocacy Lead, working with Google AI Research and product teams, and earlier was a senior developer evangelist at Microsoft. He holds a physics and computer science degree from Cardiff University, wrote a 2025 PyTorch follow-up to this book, and has published science fiction novels.

Questions

Is AI and Machine Learning for Coders worth reading in 2026?
It remains a clear introduction to neural network fundamentals such as computer vision, text processing and sequence models, taught through working code. However, it uses 2020-era TensorFlow and does not cover transformers or large language models. Readers starting fresh may prefer Moroney's 2025 follow-up, AI and ML for Coders in PyTorch, which adds generative AI.
Do I need math to read AI and Machine Learning for Coders?
Very little. Moroney deliberately explains concepts such as convolutional filters, embeddings and loss functions through code rather than equations, and assumes basic Python skills rather than calculus or linear algebra. Readers who later want the mathematical foundations will need a separate textbook, but the book is designed so programmers can build working models first.
What does AI and Machine Learning for Coders cover?
The first half builds TensorFlow models for computer vision, natural language processing and time-series prediction. The second half covers deployment: TensorFlow Lite on Android and iOS, TensorFlow.js in the browser, TensorFlow Serving on servers, and federated learning, followed by a closing chapter on AI ethics, fairness and privacy. Throughout, examples are working Python code.

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.