What do you think?
Rate this book
Deep Learning Illustrated: A Visual, Interactive Guide to Artificial Intelligence
Deep learning is transforming software, facilitating powerful new artificial intelligence capabilities, and driving unprecedented algorithm performance. Deep Learning Illustrated is uniquely intuitive and offers a complete introduction to the discipline's techniques. Packed with full-color figures and easy-to-follow code, it sweeps away the complexity of building deep learning models, making the subject approachable and fun to learn.
World-class instructor and practitioner Jon Krohn--with visionary content from Grant Beyleveld and beautiful illustrations by Agla� Bassens--presents straightforward analogies to explain what deep learning is, why it has become so popular, and how it relates to other machine learning approaches. Krohn has created a practical reference and tutorial for developers, data scientists, researchers, analysts, and students who want to start applying it. He illuminates theory with hands-on Python code in accompanying Jupyter notebooks. To help you progress quickly, he focuses on the versatile deep learning library Keras to nimbly construct efficient TensorFlow models; PyTorch, the leading alternative library, is also covered.
You'll gain a pragmatic understanding of all major deep learning approaches and their uses in applications ranging from machine vision and natural language processing to image generation and game-playing algorithms.
Discover what makes deep learning systems unique, and the implications for practitioners Explore new tools that make deep learning models easier to build, use, and improve Master essential theory: artificial neurons, training, optimization, convolutional nets, recurrent nets, generative adversarial networks (GANs), deep reinforcement learning, and more Walk through building interactive deep learning applications, and move forward with your own artificial intelligence projects Register your book for convenient access to downloads, updates, and/or corrections as they become available. See inside book for details.
World-class instructor and practitioner Jon Krohn--with visionary content from Grant Beyleveld and beautiful illustrations by Agla� Bassens--presents straightforward analogies to explain what deep learning is, why it has become so popular, and how it relates to other machine learning approaches. Krohn has created a practical reference and tutorial for developers, data scientists, researchers, analysts, and students who want to start applying it. He illuminates theory with hands-on Python code in accompanying Jupyter notebooks. To help you progress quickly, he focuses on the versatile deep learning library Keras to nimbly construct efficient TensorFlow models; PyTorch, the leading alternative library, is also covered.
You'll gain a pragmatic understanding of all major deep learning approaches and their uses in applications ranging from machine vision and natural language processing to image generation and game-playing algorithms.
Discover what makes deep learning systems unique, and the implications for practitioners Explore new tools that make deep learning models easier to build, use, and improve Master essential theory: artificial neurons, training, optimization, convolutional nets, recurrent nets, generative adversarial networks (GANs), deep reinforcement learning, and more Walk through building interactive deep learning applications, and move forward with your own artificial intelligence projects Register your book for convenient access to downloads, updates, and/or corrections as they become available. See inside book for details.
416 pages, Paperback
Published September 18, 2019
139 people are currently reading
427 people want to read
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
Displaying 1 - 19 of 19 reviews
December 5, 2019
This book got me into Deep Learning. This is a high-level overview that any software engineer will desire as we try to understand “this new world” (even as of 2019). The terms in new-world are used in multiple Medium articles, and github.io pages and github.com READMEs, and we wonder what any of these have to do with solving the problem, how does it fit in, etc. This book took a top-down approach to explain it all and help me made sense of every article that I read about Deep Learning, Convolutional Neural Networks, and Artificial Intelligence as of 2019. I like to thank the Authors for their invaluable and accessible contribution to this field of AI and Neural Networks.
May 25, 2020
A really good beginner/intermediate overview of deep learning. I liked how the authors explained deep learning from basic building blocks and then stacking them up and combining them to teach higher-level concepts. Also, the illustrated approach and giving context around the real-world applications also helped as much as the illustrations to make the curve of learning gentler. Many other books in this space directly dive into the math.
The book covers a wide variety of neural network architectures (CNNs, RNNs, Reinforcement deep learning, and more) and applications (machine vision, game-playing, natural language processing, and more). The python notebook code which accompanies the book makes the learning practical. Also the pointers to papers as well a online resources are a really useful part of the book. I would rate the book 4.5 stars.
The book covers a wide variety of neural network architectures (CNNs, RNNs, Reinforcement deep learning, and more) and applications (machine vision, game-playing, natural language processing, and more). The python notebook code which accompanies the book makes the learning practical. Also the pointers to papers as well a online resources are a really useful part of the book. I would rate the book 4.5 stars.
November 10, 2019
The book is a good introduction to deep learning. It covers different prominent kinds of DL with Keras based examples.
I picked up the book for the "illustrated" part and I did not find it illustrative. While the topics are described with simple Keras based examples and explanation of each line of code (which is good), I wouldn't consider this illustrated for two reasons. First, Keras is a high level API that very nicely abstracts the details of DL. So, explaining the examples in terms of Keras API fails to illustrate. Second, there is no walk through/step-by-step/unrolling of at least one example for each 'kind" of DL. Specifically, no illustration of back propagation. Like most books, the analytical exposition of back prop in terms of formulae is provided in an appendix but never illustrated with an example. Since back prop is a key component of DL, I expected an illustration of back prop.
Overall, another good introductory book about the "what" and some of the "how" of DL.
Update: For folks looking illustrative exposition, you might want to try out "Deep Learning from Scratch" (at least based on what I have seen so far in chapter 1 of the book).
I picked up the book for the "illustrated" part and I did not find it illustrative. While the topics are described with simple Keras based examples and explanation of each line of code (which is good), I wouldn't consider this illustrated for two reasons. First, Keras is a high level API that very nicely abstracts the details of DL. So, explaining the examples in terms of Keras API fails to illustrate. Second, there is no walk through/step-by-step/unrolling of at least one example for each 'kind" of DL. Specifically, no illustration of back propagation. Like most books, the analytical exposition of back prop in terms of formulae is provided in an appendix but never illustrated with an example. Since back prop is a key component of DL, I expected an illustration of back prop.
Overall, another good introductory book about the "what" and some of the "how" of DL.
Update: For folks looking illustrative exposition, you might want to try out "Deep Learning from Scratch" (at least based on what I have seen so far in chapter 1 of the book).
Want to read
October 14, 2022DataScience and ML plan:
(0) Ace the Data Science Interview (Kevin Huo)
(1) Business Data Science
(2) Naked Statistics — Stripping the Dread From the Data
(3) Machine Learning Simplified
(4) Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow, 3rd Edition
(5) Practical Statistics for Data Scientists
(6) Elements of Statistical Learning
(7) Machine Learning Yearning
(8) Artificial Intelligence in Practice: How 50 Successful Companies Used AI
(9) Deep Learning Illustrated
(10) Deep Learning with Python
(11) Deep Learning (by Ian Goodfellow et al)
(12) Interpretable Machine Learning with Python
(13) Mastering 'Metrics: The Path from Cause to Effect
(0) Ace the Data Science Interview (Kevin Huo)
(1) Business Data Science
(2) Naked Statistics — Stripping the Dread From the Data
(3) Machine Learning Simplified
(4) Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow, 3rd Edition
(5) Practical Statistics for Data Scientists
(6) Elements of Statistical Learning
(7) Machine Learning Yearning
(8) Artificial Intelligence in Practice: How 50 Successful Companies Used AI
(9) Deep Learning Illustrated
(10) Deep Learning with Python
(11) Deep Learning (by Ian Goodfellow et al)
(12) Interpretable Machine Learning with Python
(13) Mastering 'Metrics: The Path from Cause to Effect
This entire review has been hidden because of spoilers.
February 12, 2020
Deep Learning Illustrated presents the AI novice (such as myself) with a thorough understanding of deep learning and its importance in building more efficient models. The ample visuals are easy to comprehend and the code notebooks (accessible through the GitHub repository associated with the book) provide a handy framework. Jon's teaching style benefits the learner by reviewing key concepts at the conclusion of each chapter and reinforcing them throughout subsequent ones. All together, the book represents a highly worthwhile dive into deep learning.
January 13, 2020
As a strong programmer who knew nothing about deep learning, what a perfect book to learn about it! Clear, friendly, authoritative, well-chosen material.
April 22, 2023
I decided to read this book because I was curious about the illustrations part. And even though I do have previous knowledge and experience with deep learning, from both my academic studies and from work, I thought it would be good to have a revision of the basics.
I'm giving it 3 stars because the title is misleading. In the beginning, there are quite a few illustrations, yes, but they get more and more infrequent as the book progresses. For the parts that do have some illustration, it is usually just a drawing of a related mathematician or graphs that are commonly present in most materials for this kind of topic.
This is a good book for beginners, but don't expect it to be "a visual, interactive guide".
I'm giving it 3 stars because the title is misleading. In the beginning, there are quite a few illustrations, yes, but they get more and more infrequent as the book progresses. For the parts that do have some illustration, it is usually just a drawing of a related mathematician or graphs that are commonly present in most materials for this kind of topic.
This is a good book for beginners, but don't expect it to be "a visual, interactive guide".
August 30, 2020
Very good high level overview of machine learning, with online examples to go deeper. Fundamental programming knowledge required to get the most out of it.
May 26, 2023
This is an excellent introduction to deep learning for those with some technical background. The only reason I deduct a star is that this field has been moving so quickly that the examples are starting to feel stale. That said, even though the book doesn't cover the latest developments or applications, it covers fundamental concepts that are still necessary for understanding more recent developments.
There are many books that do that, so what makes this one special? Despite the title, it's not the illustrations. Although they are useful and were the hook that got my attention, they are not what makes the book great. What makes the book great is that it builds up complexity in layers so that a reader can go from vaguely familiar with deep learning concepts through comfortably reading about, for example, an actual implementation of a digit classifier using convolutional neural nets.
The authors achieve this by structuring the book into three layered parts which use the same examples. The first part gives a high level overview of uses of deep learning by telling the story of its roots in biological and machine vision. It then discussions applications in text processing, image understanding and generation, and game-playing. Part two covers the essential theory of machine learning, building up piece from artificial neurons to defining, training, and improving deep networks. There is a lot of technical substance here, but by building it up bit-by-bit, the reader is able to follow along without too much effort. The third part goes back to the applications from part one and shows applied examples in these domains, touching upon concepts specific to that domain. Throughout, the book is filled with real code examples.
This layered technique to presenting these ideas makes it easy for the reader to build up knowledge. The use of practical examples anchors the knowledge in practice and helps build up intuition by connecting theoretical concepts to real numbers. The use of repeated examples is especially valuable because it allows the reader to understand how using more sophisticated techniques impact the results, often for the better but sometimes not.
Overall, I strongly recommend this book, despite it being three years old in a field where three weeks feels like a long time.
There are many books that do that, so what makes this one special? Despite the title, it's not the illustrations. Although they are useful and were the hook that got my attention, they are not what makes the book great. What makes the book great is that it builds up complexity in layers so that a reader can go from vaguely familiar with deep learning concepts through comfortably reading about, for example, an actual implementation of a digit classifier using convolutional neural nets.
The authors achieve this by structuring the book into three layered parts which use the same examples. The first part gives a high level overview of uses of deep learning by telling the story of its roots in biological and machine vision. It then discussions applications in text processing, image understanding and generation, and game-playing. Part two covers the essential theory of machine learning, building up piece from artificial neurons to defining, training, and improving deep networks. There is a lot of technical substance here, but by building it up bit-by-bit, the reader is able to follow along without too much effort. The third part goes back to the applications from part one and shows applied examples in these domains, touching upon concepts specific to that domain. Throughout, the book is filled with real code examples.
This layered technique to presenting these ideas makes it easy for the reader to build up knowledge. The use of practical examples anchors the knowledge in practice and helps build up intuition by connecting theoretical concepts to real numbers. The use of repeated examples is especially valuable because it allows the reader to understand how using more sophisticated techniques impact the results, often for the better but sometimes not.
Overall, I strongly recommend this book, despite it being three years old in a field where three weeks feels like a long time.
October 26, 2021
An Outstanding Book. This has cleared a lot of qualms I had with understanding Neural Networks. I salute to the authors for taking a simple and plausible approach to this emerging descipline.
Those who have a tiny bit of programming experience and have their feet into almost all desciplines of knowledge, a a lot of curiostiy will find A.I to be a taste on their buds. Its outstanding.
Those who have a tiny bit of programming experience and have their feet into almost all desciplines of knowledge, a a lot of curiostiy will find A.I to be a taste on their buds. Its outstanding.
August 8, 2021
A must-read for every Deep Learning student.
January 9, 2022
Just finish and getting ready to crack open Chollet's 2nd Edition of Deep Learning with Python. We will see how they compare.
May 12, 2022
Just finished reading Deep Learning Illustrated and absolutely loved it. It really clarified what deep learning was for me which will really help me in my studies and side projects!
January 12, 2023
Nice resource for beginners that's fun to read.
May 5, 2023
A truly excellent introduction to deep learning. I thoroughly enjoyed this read. My sincere thanks to the authors for distilling complex concepts into easy to read prose.
June 17, 2021
I have tried almost all the famous books of Deep Learning and undoubtedly "Deep Learning Illustrated" is the best book in this area, and it is highly recommended.
This book delivers an entertaining account and perspective on Deep Learning. While being trained, the reader is taken on a journey through the world of Deep Learning from the creation to its development.
Each chapter is filled with illustrations and information of that area and ends with useful key notes. These features plus Goldilocks-style make it unique and more interesting to read, learn and enjoy.
The author, Dr. Jon Krohn, is a proven scientist specializing in Deep Learning, who supplies an in-depth insight of various aspects of it.
Overall, this book is an excellent resource to students, educators, scientists, researchers and Deep Learning enthusiasts.
This book delivers an entertaining account and perspective on Deep Learning. While being trained, the reader is taken on a journey through the world of Deep Learning from the creation to its development.
Each chapter is filled with illustrations and information of that area and ends with useful key notes. These features plus Goldilocks-style make it unique and more interesting to read, learn and enjoy.
The author, Dr. Jon Krohn, is a proven scientist specializing in Deep Learning, who supplies an in-depth insight of various aspects of it.
Overall, this book is an excellent resource to students, educators, scientists, researchers and Deep Learning enthusiasts.
December 1, 2020
Deep Learning Illustrated by Jon Krohn, Grant Beyleveld, and Aglaé Bassens is just fantastic. Very well explained, with clear visuals and practical exercises.
An insightful ML (Deep learning) book you must read in 2020!
An insightful ML (Deep learning) book you must read in 2020!
June 19, 2021
One star for the entirely misleading title. The book is *less* illustrated than most of the best books in the field. Otherwise the content is not bad, but far from the top, perhaps 3 stars.
April 26, 2022
shallow book on deep learning, the only formula has a typo, basically both useless for professional purposed and too crammed with information to be a simple overview
Displaying 1 - 19 of 19 reviews