This wasn't what I expected at all. There wasn't much explanation here. I did learn a few things, but nothing that was worth the price of this book. There are some nice utility code snippets, but I didnt really learn the internals of how keras work. If you dont need to dive deep into the keras api, you should be fine with this.
2.0 out of 5.0 -
by Harlan R. Seymour on Oct. 27, 2017
Major part of book is walking through source code from keras.ai and github repositories, with just hand waving explanation. Half the book is copy & pasted source code and images from code runs. There is no real depth of explanation. If you want a quick introduction to Keras this could be a good book for you. If you are looking to get a deeper understanding then this book is a miss.
4.0 out of 5.0 -
by Shahroz Sohail on Dec. 30, 2017
Served its purpose well, however I feel it should definitely be supplemented on a book with more theory on neural networks, and the chapter on reinforcement learning started off well but had way to much code without explanation.
5.0 out of 5.0 -
by Tim on Sept. 20, 2017
Excellent book. Enough detail to get moving, just short enough to fully digest
5.0 out of 5.0 -
by Sandro Skansi on June 28, 2017
It is a great book. It is not a textbook on deep learning, it is a ``textbook'' on Keras. If you do not know how an LSTM works, you should learn it and then return (I would suggest the great blog by Christopher Olah for LSTMs in particular). Or you could go for the Goodfellow and Bengio book. This book has a number of well worked examples, and I have found only a minor flaw in the code which can be fixed with a quick Google search, so it is nothing to worry about. Then again, I do not know of any book with code examples that has code that works right away (i.e. where every single line of code from the book works right away). I was a bit discouraged by the 1 star reviews but I bought the book nevertheless (in Kindle so if the book is as bad as the two reviewers would suggest that I could return the book). But fortunately they were wrong. It is not a perfect book, but then again we are not giving kidneys to sick family members, but stars to a book--perhaps it is not a five star book, but it certainly is a 4.94 star book and it is well worth the 40 USD.
5.0 out of 5.0 -
by Melvin on Dec. 30, 2017
I felt compelled to write a review because I really think this is an exceptionally good book under the circumstances. When I say "under the circumstances", I mean given the fact that deep learning is a challenging topic to explain and requires both a theoretic and practical approach to be appreciated. The author clearly avoids getting bogged down with the theoretical aspects and I can appreciate why since a thorough theoretical understanding would require a separate book in it's own right.This book will not help you understand the theory or underlying mathematics. However, if you already understand the theory and want to learn to use a package like Keras then this is the book for you. This book stands out because it gives details about the implementation aspects of coding many different deep learning models that you will hear about in the literature and in the field. For example, LeNet, ResNet, etc. among many others are demonstrated through out the book. Generally speaking, topics in deep learning are not easy to explain to the average reader and I think the author recognizes this difficulty and chooses to place his focus on demonstrating how to implement deep learning methods and being careful to explain what the different modules do and their respective parameters. In my view, this book is very suitable for Data Scientists who already know the spectrum of machine learning models and techniques and want to get their hands dirty as fast as possible with deep learning. This book is a much better practical book for deep learning than the popular book by Aurélien Géron called "Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems". I have looked at many deep learning books and in my view this one did the best job is getting me comfortable with implementing deep learning models on my own. The one thing that I found the book was lacking is that it's final chapter on AI and reinforcement learning did not seem as thorough and detailed as the other chapters in the book. Having reviewed many books in the area of deep learning, I can honestly say this is probably the best book I have come across so far. However, I came to this book already having a solid understand of deep learning theory.
1.0 out of 5.0 -
by RSG on Nov. 12, 2017
Not a good book. The table of contents is excellent but in reality it's just a collection of various and sundry screenshots without any coherence or continuity. It was obviously thrown together to capitalize on the current deep learning meme. If you want to learn deep learning, start with Ian Goodfellow's superb "Deep Learning" text and Andrew Ng's Coursera courses. By the time you finish those, there will be plenty of good Keras books to choose from.
3.0 out of 5.0 -
by Andrew Jennings on Dec. 17, 2017
This is a useful book. In essence it is a series of examples with the code associated. The code works and the comments are helpful. It doesn't elaborate any of the techniques, so you will have to look elsewhere for deeper understanding. If you know where to look for examples then it won't be much use to you. If you don't know where to look then it is a very useful guidebook.
5.0 out of 5.0 -
by Civardi Francesco on June 7, 2017
Keras can be used, as a high-level framework to experiment and develop Deep Learning solutions, on top of Theano, Tensorflow and, since a few days (Jun 17), even on top of Microsoft CNTK and Mxnet. I personally use some of them, and I only need to write in Keras, independently from the backend. Deep Learning with Keras is a nice hands-on handbook that covers the new Keras 2.0 release. You can use it as an entry point, or to learn about the most advanced topics, like Generative Adversarial Networks. It covers ConvNet, GA, RNN, Word Embedding, Reinforcement learning etc. Of course you need to know some Python and Numpy, but they are not so difficult. The book has also a lot of example, that really help. For instance, it helped me better understanding generators, so I can train neural networks on big data that don't fit in the memory (tens of thousands of medical MRI). Transfer learning is also very well explained with code. The Keras web site is nice, but for somebody like me (I'm a data scientist, not a "real programmer" or developer) code examples are really needed to understand how to apply the concepts. So I strongly suggest this book. Thank you Antonio and Sujit for writing it!
3.0 out of 5.0 -
by JP on July 5, 2017
Read half of it. The examples are ok but the theory explanation of what you are doing are very basic - not enough to understand the theory without some further background. And the coding part is just a cookbook presentation - here it is. Not a lot of depth. Have not tried to run the code samples yet. I was hoping for a bit more. Maybe given that keras sits on top of tensorflow or Theano there is just not as much to say? This book contains many code examples and log traces showing execution of the code. The code and log traces are formatted like code on a computer screen and look very washed out (print book). Bolder fonts and a little ink would have made this book a lot easier to read. This also gives you an idea what this book is like - screen shots of code followed by screen shots of code execution.