Deep Learning: A Visual Approach

by Andrew Glassner

An accessible, highly-illustrated introduction to deep learning that offers visual and conceptual explanations instead of equations. You'll learn how to use key deep learning algorithms without the need for complex math.

Ever since computers began beating us at chess, they've been getting better at a wide range of human activities, from writing songs and generating news articles to helping doctors provide healthcare.

Deep learning is the source of many of these breakthroughs, and its remarkable ability to find patterns hiding in data has made it the fastest growing field in artificial intelligence (AI). Digital assistants on our phones use deep learning to understand and respond intelligently to voice commands; automotive systems use it to safely navigate road hazards; online platforms use it to deliver personalized suggestions for movies and books - the possibilities are endless.

Deep Learning: A Visual Approach is for anyone who wants to understand this fascinating field in depth, but without any of the advanced math and programming usually required to grasp its internals. If you want to know how these tools work, and use them yourself, the answers are all within these pages. And, if you're ready to write your own programs, there are also plenty of supplemental Python notebooks in the accompanying Github repository to get you going.

The book's conversational style, extensive color illustrations, illuminating analogies, and real-world examples expertly explain the key concepts in deep learning,

   '   How text generators create novel stories and articles
   '   How deep learning systems learn to play and win at human games
   '   How image classification systems identify objects or people in a photo
   '   How to think about probabilities in a way that's useful to everyday life
   '   How to use the machine learning techniques that form the core of modern AI

Intellectual adventurers of all kinds can use the powerful ideas covered in Deep Learning: A Visual Approach to build intelligent systems that help us better understand the world and everyone who lives in it. It's the future of AI, and this book allows you to fully envision it.

Genres: Artificial Intelligence, Technology, Science, Nonfiction, Technical, Computer Science, Programming

736 pages, Paperback

Published June 29, 2021

Reviews

[Jay · Rating 5 out of 5]

When you have a book like this, broad and deep, you try and see if it really knows the subject by paying attention to the sections you do know something about. This is how I evaluated this book before purchase.

I looked up Principal Component Analysis, something I have some familiarity with. I read that section in detail to get a feel for the author's capability of explaining a difficult topic. It is the best explanation I've ever read. On that alone, I purchased the book.

I haven't been disappointed. The author's use of visuals certainly earns it the right to use its subtitle. I'm still working my way through other portions of the book, but for those that I do have experience with, I've learned even more.

In essence, while the promise of no math is a bit optimistic, the book does what it claims to do. I still think you need to understand the math to fully grok the subjects in the book, but this is a great way to approach it when combined with another book that might have more mathematical insights.

[Jay · Rating 5 out of 5]

Un manuale eccezionale. Difficile certamente da leggere, almeno per me che ho una formazione prettamente umanistica, ma Glassner ti conduce sulla giusta strada per comprendere i fondamenti del machine learning e del deep learning. Posso tranquillamente dire che ha salvato la mia tesi sulle AI generative. Per gli appassionati, è un manuale da tenersi stretti.

"We should remember to always use deep learning, like all of our tools,
to bring out the best in humanity, and make the world a better place for
everyone."

[Mitchell · Rating 5 out of 5]

This is a good introductory book on deep learning, but it does not mean that you are an introductory book after reading it. As the saying goes, "a picture is worth a thousand words", I think statistics and Data Science are very interesting disciplines because they use data visualization techniques to illustrate and analyze the underlying relationships between data. As its name suggests, this book uses a large number of Visual Graphs to illustrate concepts in AI fields such as statistical probability, machine learning, deep learning, CNN, GAN, RNN, and Transformer, helping readers gain an intuitive understanding. The paper that proposed ZF-Net in 2013 used visual analysis to analyze why CNNs such as LeNet and AlexNet can work well. I also often feel that some good teachers can use simple language to describe complex concepts, but this method is suitable for outsiders. Practitioners still need to understand the formulas and mathematical principles of algorithms such as FF and BP.

[Elie De Brauwer · Rating 5 out of 5]

Truly enjoyed reading this book, the absence of math (looking at you Mr Goodfellow) makes this book quite enjoyable. Even though in the later chapters this becomes a bit of a struggle. That being said the author really covers a lot of ground and touches a lot of advanced topics. I do doubt that it would be an 'easy read' for people without any prior background as it still remains a quite steep domain.

[Craig Beyers · Rating 5 out of 5]

This is a thorough, in-depth book about machine learning and what the media call artificial intelligence, or “AI”. It’s technical so it may be a difficult, but worthwhile, read. I’m not sure yuo’ll enjoy it but you will learn something!

[Rick Sam · Rating 5 out of 5]

Excellent Work.

Too long to summarize concisely.

Deus Vult
Gottfried

[David · Rating 5 out of 5]

This book is light on math and heavy on concepts. If you're a technical manager of machine learning staff and want a better intuition about the technologies, you should read this, cover to cover.

[Petr Lorenc · Rating 5 out of 5]

Very good and complete explanation of wide topics in ML. Recommended

[Roman Michnica · Rating 5 out of 5]

Awesome explanations of all topics .

[Jfzhang · Rating 5 out of 5]

Good to understand DL without much mathematical knowledge. You can easily know how DL works and what problems it can solve.

[Keith Woodruff · Rating 5 out of 5]

Would be drowning in neural networks without this. Great life preserver.

[Simon Lee · Rating 5 out of 5]

the author write in a clear way that includes pictures and diagram. He explains the core concept well.