Deep Learning with Python, Second Edition
by: Francois Chollet (0)
In Deep Learning with Python, Second Edition you will learn:
   Deep learning from first principles    Image classification and image segmentation    Timeseries forecasting    Text classification and machine translation    Text generation, neural style transfer, and image generation    Full color printing throughout
Deep Learning with Python has taught thousands of readers how to put the full capabilities of deep learning into action. This extensively revised full color second edition introduces deep learning using Python and Keras, and is loaded with insights for both novice and experienced ML practitioners. Youâll learn practical techniques that are easy to apply in the real world, and important theory for perfecting neural networks.
Purchase of the print book includes a free eBook in PDF, Kindle, and ePub formats from Manning Publications.
About the technology Recent innovations in deep learning unlock exciting new software capabilities like automated language translation, image recognition, and more. Deep learning is quickly becoming essential knowledge for every software developer, and modern tools like Keras and TensorFlow put it within your reachâeven if you have no background in mathematics or data science. This book shows you how to get started.
About the book Deep Learning with Python, Second Edition introduces the field of deep learning using Python and the powerful Keras library. In this revised and expanded new edition, Keras creator François Chollet offers insights for both novice and experienced machine learning practitioners. As you move through this book, youâll build your understanding through intuitive explanations, crisp color illustrations, and clear examples. Youâll quickly pick up the skills you need to start developing deep-learning applications.
What's inside
   Deep learning from first principles    Image classification and image segmentation    Time series forecasting    Text classification and machine translation    Text generation, neural style transfer, and image generation    Full color printing throughout
About the reader For readers with intermediate Python skills. No previous experience with Keras, TensorFlow, or machine learning is required.
About the author François Chollet is a software engineer at Google and creator of the Keras deep-learning library.
Table of Contents 1Â What is deep learning? 2 The mathematical building blocks of neural networks 3 Introduction to Keras and TensorFlow 4 Getting started with neural networks: Classification and regression 5 Fundamentals of machine learning 6 The universal workflow of machine learning 7 Working with Keras: A deep dive 8 Introduction to deep learning for computer vision 9 Advanced deep learning for computer vision 10 Deep learning for timeseries 11 Deep learning for text 12 Generative deep learning 13 Best practices for the real world 14 Conclusions
The Reviews
I have more than 50 books on AI & ML, but Francois Chollet's bible on DL (first edition) is the only one which is open on my desk since 2018.The author decision to focus on working Python code instead of the math behind it - was crucial for its amazing success.As others have mentioned - Chollet is an excellent teacher which can explain complex and complicated ideas to the masses. I have used his code and DL techniques successfully in many projects, hackathons and Kaggle competitions.I've just received my second edition a couple of days ago - and the book is about 50% bigger than the first edition, as the author has added more examples and details plus full color printing.Strongly recommended to any aspiring data scientist.
This book is ideally suited to people who want a meaningful introduction into the most important contemporary concepts in Deep Learning. The book is accessible to people who lack both programming and linear algebra. Neither are needed to get a full understanding of everything the book offers.IMO, the greatest moments in the book are the asides that appear in every chapter. The author will take a paragraph to note in passing things like '... no one really knows for sure why batch normalization helps. There are various hypotheses, but no certitudes." Or, "Importantly, I would generally recommend placing the previous layer's activation after the batch normalization layer (although this is still a subject of debate)." There is even an entire chapter dedicated to musings on the future of Deep Learning and general AI. This is the cherry on top that you don't get with most offers. Chollet offers them in nearly every chapter.The book may as well have been called "Deep Learning with Keras" and that's not a bad thing. All the code is freely downloadable and can be run for free on a Google platform. You can freely ignore the implementation details and Python and simply run and learn from the notebooks provided. NOTE: As of February 2022, the new M1 Macs have bugs in the implementation of tensorflow that prevent a few code samples from working correctly. AND, some examples take so long to run (many hours) that there may be issues running them at Google. Frustrating though it might be, it does not detract from the experience.As to cons, I don't see enough to warrant taking a star off the review. All important concepts are covered at an introductory level. The code works. The writing is clear. The author is an expert. There is a bizarre convention of having diagrams flow from the bottom to the top instead of top-down.It's a good intro and basic reference. You'll get into more depth by taking the OpenAI courses at Coursera, but I'd actually recommend those as a next step after fully absorbing this book. Recommended.While the book is titled "Deep Learning with Python", it might have been better titled, "Deep Learning with Keras." While Python is ostensibly
I pre-ordered the 2nd Edition because I loved the 1st Edition so much. I am still in the midst of working through the book, and I am finding it extremely useful, informative, interesting, and insightful. It is simply one of the best resources I have come across on this subject. Period. Kudos to Francois Chollet for his contribution to democratizing the development and deployment of AI technology. He is truly an amazing teacher as well!
This book is fantastic! Extremely well written, easy to follow for anyone with some programming experience. Francois is a master in the field and the book is accessible, up to date, and an excellent way to jumpstart a career in machine learning!
This is a thoughtful book with excellent coverage of trust issues, ML methods and what to do about issues. A good hadbook.
Just bought the book again (second edition) ... this book is not only about using Keras and Tensorflow, but it provides a much broader understanding of deep learning and practical approached to train deep neural networks.
This book pairs well with https://www.amazon.com/Hands-Machine-Learning-Scikit-Learn-TensorFlow/dp/1492032646 as that book spends a lot of time surveying the field of Machine Learning from first principles and works its way up to Deep Learning in the second half of the book. Chollet on the other hand dives right into deep learning and there's not even a description or diagram of artificial neurons, the perceptron, or even much explanation of what the matrix multiplication is doing from a conceptual point of view.Instead, he basically tells you "This is a Layer and here is how it's evaluated, now let's make models!" (he definitely does not seem to be a fan of any of the common biological analogies).By skipping most all of the history and old ideas that got us where we are today, he is able to fill the book with really useful outlines/recipes for all the big applications of modern Deep Learning (where modern means 2021 not 2018 for example).The book is entirely based around Keras and again avoids talking much about the lower-level TensorFlow APIs, preferring to stick to the Keras API and its good default choices which makes the examples very simple and straightforward.The world of Machine Learning has, for a while, been diverging into two paths, that of the Researcher and that of the Practitioner, and this is definitely a book for the practitioner who is less worried about all the math and theory. If you only want to get one ML book that will quickly launch you into being able to do practical real-world stuff, then I would say this should be the one. You won't get the full classic Machine Learning background (I recommend the other book as a supplement if you want more of that).This book is also much more up to date than even the "Hands On..." book which is two years old now (practically a lifetime in this field). For that reason alone, this is a must have right now.
Why such a huge price difference between Amazon and Manning ($32.99)? Although I have only read the 1st edition, and it was fantastic, I'm sure 2nd edition is even better given the author's stellar reputation. Match the price Amazon and I'll buy it.
easy to readcolorful picturescodes are well-explained
Incredibly well presented material that conveys the author's (obviously extensive) knowledge to the Keras layperson (though a bit of Python experience is presumed). This content is approachable for the Machine Learning neophyte without being overwhelming. A beautifully-delivered and finely tuned set of reasoned funnels that make it feel as though the reader, him/herself has concluded what the correct path should be, because "it's obvious" as you continue reading. I have many, many Machine Learning books. This one is the first one that - after reading a paragraph, I say "But, of COURSE!" Brilliantly presented and deftly navigated. Bravo!
