Jon Krohn - Deep Learning Illustrated: A Visual, Interactive Guide to Artificial Intelligence

Over the next few decades, artificial intelligence is poised to dramatically change almost every aspect of our lives, in large part due to todays breakthroughs in deep learning. The authors clear visual style provides a comprehensive look at whats currently possible with artificial neural networks as well as a glimpse of the magic thats to come.

Tim Urban, writer and illustrator of Wait But Why

This book is an approachable, practical, and broad introduction to deep learning, and the most beautifully illustrated machine learning book on the market.

Dr. Michael Osborne, Dyson Associate Professor in Machine Learning, University of Oxford

This book should be the first stop for deep learning beginners, as it contains lots of concrete, easy-to-follow examples with corresponding tutorial videos and code notebooks. Strongly recommended.

Dr. Chong Li, cofounder, Nakamoto & Turing Labs; adjunct professor, Columbia University

Its hard to imagine developing new products today without thinking about enriching them with capabilities using machine learning. Deep learning in particular has many practical applications, and this books intelligible clear and visual approach is helpful to anyone who would like to understand what deep learning is and how it could impact your business and life for years to come.

Helen Altshuler, engineering leader, Google

This book leverages beautiful illustrations and amusing analogies to make the theory behind deep learning uniquely accessible. Its straightforward example code and best-practice tips empower readers to immediately apply the transformative technique to their particular niche of interest.

Dr. Rasmus Rothe, founder, Merantix

This is an invaluable resource for anyone looking to understand what deep learning is and why it powers almost every automated application today, from chatbots and voice recognition tools to self-driving cars. The illustrations and biological explanations help bring to life a complex topic and make it easier to grasp fundamental concepts.

Joshua March, CEO and cofounder, Conversocial; author of Message Me

Deep learning is regularly redefining the state of the art across machine vision, natural language, and sequential decision-making tasks. If you too would like to pass data through deep neural networks in order to build high-performance models, then this bookwith its innovative, highly visual approachis the ideal place to begin.

Dr. Alex Flint, roboticist and entrepreneur

Deep Learning Illustrated

A Visual, Interactive Guide to Artificial Intelligence

Jon Krohn
with Grant Beyleveld
and Agla Bassens

Boston Columbus New York San Francisco Amsterdam Cape Town
Dubai London Madrid Milan Munich Paris Montreal Toronto Delhi Mexico City
So Paulo Sydney Hong Kong Seoul Singapore Taipei Tokyo

Many of the designations used by manufacturers and sellers to distinguish their products are claimed as trademarks. Where those designations appear in this book, and the publisher was aware of a trademark claim, the designations have been printed with initial capital letters or in all capitals.

The authors and publisher have taken care in the preparation of this book, but make no expressed or implied warranty of any kind and assume no responsibility for errors or omissions. No liability is assumed for incidental or consequential damages in connection with or arising out of the use of the information or programs contained herein.

For information about buying this title in bulk quantities, or for special sales opportunities (which may include electronic versions; custom cover designs; and content particular to your business, training goals, marketing focus, or branding interests), please contact our corporate sales department at or (800) 382-3419.

For government sales inquiries, please contact .

For questions about sales outside the U.S., please contact .

Visit us on the Web: informit.com/aw

Library of Congress Number: 2019938790

Copyright 2020 Pearson Education, Inc.

Cover art by Agla Bassens

All rights reserved. This publication is protected by copyright, and permission must be obtained from the publisher prior to any prohibited reproduction, storage in a retrieval system, or transmission in any form or by any means, electronic, mechanical, photocopying, recording, or likewise. For information regarding permissions, request forms and the appropriate contacts within the Pearson Education Global Rights & Permissions Department, please visit www.pearsoned.com/permissions/.

ISBN-13: 978-0-13-511669-2

ISBN-10: 0-13-511669-4

ScoutAutomatedPrintCode

For Gigi

Jon

Figures

Santiago Cajal (18521934)

A hand-drawn diagram from Cajals (1894) publication showing the growth of a neuron (ae) and contrasting neurons from frog (A), lizard (B), rat (C), and human (D) samples

The reading trilobite enjoys expanding your knowledge

This trilobite calls attention to tricky passages of text

The number of species on our planet began to increase rapidly 550 million years ago, during the prehistoric Cambrian period

A bespectacled trilobite

The Nobel Prize-winning neurophysiologists Torsten Wiesel (left) and David Hubel

Hubel and Wiesel used a light projector to present slides to anesthetized cats while they recorded the activity of neurons in the cats primary visual cortex

A simple cell in the primary visual cortex of a cat fires at different rates, depending on the orientation of a line shown to the cat

A caricature of how consecutive layers of biological neurons represent visual information in the brain of, for example, a cat or a human

Regions of the visual cortex

Abridged timeline of biological and machine vision, highlighting the key historical moments in the deep learning and traditional machine learning approaches to vision that are covered in this section