Zefs Guide to Deep Learning
Free!
Minimum price
$35.00
Suggested price

Zefs Guide to Deep Learning

About the Book

Zefs Guide to Deep Learning is a short guide to the most important concepts in deep learning, the technique at the center of the current artificial intelligence revolution. It will give you a strong understanding of the core ideas and most important methods in deep learning. This book presents the foundational concepts behind machine learning, neural networks, and the recent major advancements in architectures and training techniques in an easy to understand way. It also covers the most important applications of deep neural networks, including computer vision, natural language processing, and beyond. Your time is valuable, Zefs Guide to Deep Learning will get you up to speed in around only 150 pages!

---->> Get the book + the flashcards together in the bundle and save! <<----

Visit zefsguides.com to get the paperback edition as well as promos and Zefs Guides merch!

The Zefs Guides series

Zefs Guide to Deep Learning is the first book in the Zefs Guides series on deep learning and its applications. It forms the ground knowledge for the other books in the series:

  • Zefs Guide to Computer Vision
  • Zefs Guide to Natural Language Processing
  • Zefs Guide to Transformers

Zefs Guides are designed to help the beginner quickly get up to speed on topics in machine learning and data science and to help the experienced practitioner push their conceptual understanding even further. They are short and to the point, covering the most important topics and ideas. They're for you if you are a job seeker looking for a role in ML/AI/DS, a student studying for exams, an experienced data person dusting off your old knowledge, or an executive seeking a better understanding of some of today's most important technologies.

Please visit zefsguides.com for more info.

  • Share this book

  • Categories

    • Computers and Programming
    • Artificial Intelligence
    • Machine Learning
    • Data Science
    • Computer Science
    • Linguistics
  • Feedback

    Email the Author(s)

About the Author

Roy Keyes
Roy Keyes

Roy Keyes has worked in data science since 2012, building and leading teams at multiple tech startups as well as consulting for clients across a wide range of industries. Prior to data science, he received a PhD in computational physics, focusing on medical applications.

You can find his website and blog at roycoding.com.

Packages

The Book
  • PDF

  • EPUB

  • WEB

  • English

Free!
Minimum price
$35.00
Suggested price
Small Team Discount (5 copies)

Get your whole team copies of Zefs Guide to Deep Learning (5 pack)

  • PDF

  • EPUB

  • WEB

  • English

$100.00
Minimum price
$110.00
Suggested price
The Metric Dozen (10 copies)

Get 10 copies of Zefs Guide to Deep Learning to distribute to your whole team

  • PDF

  • EPUB

  • WEB

  • English

$180.00
Minimum price
$220.00
Suggested price
The Century Pack (100 copies)

Get a copy of Zefs Guide to Deep Learning for everyone you know. Perfect for conference giveaways, etc.

  • PDF

  • EPUB

  • WEB

  • English

$1,000.00
Minimum price
$1,000.00
Suggested price

Bundles that include this book

$60.00
Bought separately
$20.00
Minimum price
$40.00
Suggested price
$69.99
Bought separately
$37.00
Bundle Price

Reader Testimonials

Emil Wallner
Emil Wallner

Resident at Google. Author of "No Degree ML"

The visualizations are fantastic. This book is super helpful for those who are looking to improve their understanding of deep learning.

Vicki Boykis
Vicki Boykis

Sr MLE at Duo, Creator of Normcore Tech

This is a fantastic, no-hype introduction to the practical considerations around deep learning both for practitioners who want to expand their ML knowledge, and for product and management teams who work adjacent to ML teams and want to have educated conversations around its use.

James Kirk
James Kirk

Co-founder and CTO of Meru Software Inc

Zefs Guide to Deep Learning succinctly covers the core concepts of machine learning. These topics are complex, but Roy's explanations and visualizations make them crystal clear, building the intuition you need to use them in practice. This is also a handy guide for managers and leaders who work around these topics and want to solidify their familiarity with them.

Nick Singh
Nick Singh

Author of "Ace the Data Science Interview"

Zefs Guide provides a clear, succinct, and direct explanation of the most important topics in ML and Deep Learning. But words only go so far – it’s the visuals which illustrate the key concepts of the field where the book and flashcards truly shine!

Ravi Mody
Ravi Mody

ML Manager Spotify

I love this book. It's full of very succinct and clean explanations of a lot of complex topics. This will be great for beginners, but also anyone who needs to review deep learning.

Chris Albon
Chris Albon

Director of ML at Wikimedia, Creator of Machine Learning Flashcards, Author of "Machine Learning with Python Cookbook"

Zefs Guide to Deep Learning is a no-nonsense, intuitive resource that is a must-buy for visual learners. Deep enough to be useful for a practitioner, but not mired in triviality.

Fausto Morales
Fausto Morales

Consulting Software Engineer Former Director of Computer Vision at Thorn

The examples and visualizations provide concrete representations of what can be difficult concepts to articulate in writing or verbally, which is great for teams who are considering whether deep learning might be a useful tool to solve specific problems ask the right questions.

Jeremy Jordan
Jeremy Jordan

Senior Machine Learning Engineer Duo

Zefs Guide to Deep Learning provides a solid introduction and illustration of the fundamental concepts of ML and deep learning. As a visual learner and thinker, I really appreciate how the illustrations help build your intuition of each topic discussed.

Binal Patel
Binal Patel

Machine learning engineer

If I was starting from scratch today this would be one of the first books I'd pick up. It has intuitive, high level explanations of the concepts behind deep learning (and machine learning in general), with enough depth to give you an idea of what you should dig into more to expand your understanding.

Table of Contents

  • Acknowledgments
  • 1 Introduction
    • Why deep learning?
    • Why this book?
    • What does this book cover and not cover?
    • How to use this book
  • 2 Machine Learning
    • What is machine learning?
    • Types of machine learning tasks and solutions
      • Regression
      • Classification
      • Supervised learning
      • Unsupervised learning
      • Self-supervised learning
      • Reinforcement learning
    • An example task
      • Predicting real estate sales prices
    • Formulating machine learning problems
    • Data sets and features
    • Measuring performance
      • Performance baselines and success thresholds
    • Model selection
    • Model training
      • Supervised learning
      • Unsupervised learning
      • Loss functions
      • Parameter optimization
      • Generalization and overfitting
      • Avoiding overfitting
      • Hyperparameters
    • Productionization
    • Common issues
    • Common machine learning models
    • From “traditional” ML to deep learning
    • References
  • 3 Neural Networks
    • What is a neural network?
    • What are some tasks that neural networks can accomplish?
    • The building blocks of neural networks
      • Activation functions
      • Neural network layers
      • Connections, weights, and biases
      • Learning via gradient descent
      • Output layers
    • What does a neural network do?
    • From basic neural networks to deep learning
    • Resources
  • 4 The rise of deep learning
    • Moving to deep neural networks
      • What made deep neural networks possible?
    • Where are we now with deep learning?
  • 5 Computer vision and convolutional neural networks
    • Computers and images
      • Computer vision tasks
      • Traditional computer vision
    • What’s hard about computer vision tasks?
    • Convolutional neural networks
      • Convolutions
      • Filter size, strides, padding, and pooling
      • A basic CNN architecture
    • Some important CNN model architectures for computer vision tasks
      • AlexNet
      • ResNet
      • U-Net for semantic segmentation
      • YOLO for object detection
      • Image generation with GANs
    • Common CNN techniques
      • Regularization
      • Data augmentation
      • Batch normalization
      • Gradient descent algorithms
      • Transfer learning
    • Summary and resources
  • 6 Natural language processing and sequential data techniques
    • Text, natural language, and sequential data
      • Types of sequential tasks
      • Traditional approaches
    • Making a neural network remember
      • The recurrent neural network
    • Creating context with embeddings
      • Embeddings
    • Architectures for sequential tasks
      • Gated recurrent units
      • Long short-term memory
      • Attention
      • Transformers
      • Applications and Transformer based architectures
    • Summary and resources
  • 7 Advanced techniques and practical considerations
    • Combining vision and language
      • Image captioning
      • Joint embeddings
      • Diffusion models
    • Self-supervised learning
      • Image-based techniques
      • Contrastive learning
    • Math topics related to deep learning
      • Linear algebra
      • Statistics and probability
      • Differential calculus
    • Machine learning engineering
      • Deep learning libraries
      • Graphical processing units and specialized hardware
      • Machine learning systems
    • Wrapping up
  • Notes

The Leanpub 60 Day 100% Happiness Guarantee

Within 60 days of purchase you can get a 100% refund on any Leanpub purchase, in two clicks.

Now, this is technically risky for us, since you'll have the book or course files either way. But we're so confident in our products and services, and in our authors and readers, that we're happy to offer a full money back guarantee for everything we sell.

You can only find out how good something is by trying it, and because of our 100% money back guarantee there's literally no risk to do so!

So, there's no reason not to click the Add to Cart button, is there?

See full terms...

80% Royalties. Earn $16 on a $20 book.

We pay 80% royalties. That's not a typo: you earn $16 on a $20 sale. If we sell 5000 non-refunded copies of your book or course for $20, you'll earn $80,000.

(Yes, some authors have already earned much more than that on Leanpub.)

In fact, authors have earnedover $13 millionwriting, publishing and selling on Leanpub.

Learn more about writing on Leanpub

Free Updates. DRM Free.

If you buy a Leanpub book, you get free updates for as long as the author updates the book! Many authors use Leanpub to publish their books in-progress, while they are writing them. All readers get free updates, regardless of when they bought the book or how much they paid (including free).

Most Leanpub books are available in PDF (for computers) and EPUB (for phones, tablets and Kindle). The formats that a book includes are shown at the top right corner of this page.

Finally, Leanpub books don't have any DRM copy-protection nonsense, so you can easily read them on any supported device.

Learn more about Leanpub's ebook formats and where to read them

Write and Publish on Leanpub

You can use Leanpub to easily write, publish and sell in-progress and completed ebooks and online courses!

Leanpub is a powerful platform for serious authors, combining a simple, elegant writing and publishing workflow with a store focused on selling in-progress ebooks.

Leanpub is a magical typewriter for authors: just write in plain text, and to publish your ebook, just click a button. (Or, if you are producing your ebook your own way, you can even upload your own PDF and/or EPUB files and then publish with one click!) It really is that easy.

Learn more about writing on Leanpub