Other Sellers on Amazon
+ $3.99 shipping
Advanced Deep Learning with TensorFlow 2 and Keras: Apply DL, GANs, VAEs, deep RL, unsupervised learning, object detection and segmentation, and more, 2nd Edition Paperback – February 28, 2020
"Devoted" by Dean Koontz
For the first time in paperback, from Dean Koontz, the master of suspense, comes an epic thriller about a terrifying killer and the singular compassion it will take to defeat him. | Learn more
Enter your mobile number or email address below and we'll send you a link to download the free Kindle App. Then you can start reading Kindle books on your smartphone, tablet, or computer - no Kindle device required.
To get the free app, enter your mobile phone number.
Frequently bought together
Customers who viewed this item also viewed
"Great visuals, code, and math. The book delivers what the deep learning practitioner needs: advanced content with replicable and reproducible results. I highly recommend this great book by Rowel Atienza."--
Bernardo F. Nunes, PhD, Lead Data Scientist, Growth Tribe Academy
"Advanced Deep Learning with TensorFlow 2 and Keras - Second Edition is a good and big step into an advanced practice direction. It's a brilliant book and consider this as a must-read for all."--
Dr. Tristan Behrens, Founding Member of AI Guild and Independent Deep Learning Hands-On Adviser
"I highly recommend this book for the curious data practitioner who wants to further solidify their knowledge of deep learning. The companion GitHub code repository is very useful and provides a hassle-free way to actually experiment with the various ideas presented in the book. If you enjoy reading technical books, but also enjoy experimenting with real code, and didn't think the two could be combined effectively - this book is here to change your perspective!"--
Danny Ma, Data Science Leader, Founder of Sydney Data Science & #DataWithDanny - an online community for aspiring data professionals
About the Author
Rowel Atienza is an Associate Professor at the Electrical and Electronics Engineering Institute of the University of the Philippines, Diliman. He holds the Dado and Maria Banatao Institute Professorial Chair in Artificial Intelligence and received his MEng from the National University of Singapore for his work on an AI-enhanced four-legged robot. He finished his Ph.D. at The Australian National University for his contribution in the field of active gaze tracking for human-robot interaction. His current research work focuses on AI and computer vision.
- Item Weight : 1.92 pounds
- Paperback : 512 pages
- ISBN-10 : 1838821651
- ISBN-13 : 978-1838821654
- Product Dimensions : 7.5 x 1.16 x 9.25 inches
- Publisher : Packt Publishing (February 28, 2020)
- Language: : English
- Best Sellers Rank: #636,445 in Books (See Top 100 in Books)
- Customer Reviews:
Top reviews from the United States
There was a problem filtering reviews right now. Please try again later.
The 1st edition is just about identical to the 2nd up to chapter 10, save for some stylistic changes, but half of chapter 10, as well as chapters 11, 12, 13, are brand new.
Everything that made the 1st edition great is till here: great exposition of the fundamentals, the math for those that'd like to dig a bit deeper, the great references, as well as clean, understandable, working code.
This book is highly recommended as a reference for those looking to move into deeper waters in the production of ML models for use cases that would strain conventional Neural Networks.
If I could, however, make a suggestion to all authors of ML books, it would be to PLEASE move away from MNIST, and the CIFAR datasets. I know these are the standard benchmarks in the field but you could just as easily cite this in your repositories and use the real estate in your books to explore other use cases such as anomaly detection in categorical data, time series, etc. This would make your books much more valuable in the hands of industry practitioners not looking to work strictly with images. So let's stop beating those horses yes?
This book is for the advanced student or experienced practitioner of artificial intelligence. It assumes you have a general level of knowledge of implementing various neural network architectures, or at least a good understanding. One caveat I would very much like to point out is that the Preface states that most of the code requires use of a GPU, which is not mentioned in the book's description. Thankfully, there are free options which mitigate this requirement, which can be found through a simple web search.
What I Like:
The introductory chapter gives enough information on Keras to allow even a novice AI developer to work through the book and get a lot out of it. As someone in the middle of beginner and expert, I appreciate things like that, as they can the reader a refresher of the material in case they haven't used it in a while. In this case, the author thoughtfully runs through examples using common neural network architectures, such as the multilayer perceptron, recurrent neural network, and convolutional neural network. Each section of the review also gives a refresher of the math at just the right level to get the reader ready for the advanced material later in the book. A final reason to appreciate the first chapter is that is gives clear and concise definitions of common terms used by AI practitioners.
The overall organization is also well done. I appreciate a book that flows well, as it greatly adds to the understanding when learning from it as well as lends to finding information easier when using it as a reference. Each chapter adds to the complexity of the reader's understanding, but gradually enough to aid with comprehension.
What I Don't Like
This is a difficult section to write. It's not that there is too much to write about, bu the opposite. This book is well written, both by structure and by prose. It's a balanced book to learn from and to refer to. It's a practitioner's book in that it focuses on code over math, but covers both. The topics covered are useful, interesting, and wide ranging. I did mention at the beginning the GPU requirement, but that's all I'm seeing right now.
What I Would Like to See
This is a great book overall. I would like to see more, either by expanding the book or writing another one. At 512 pages and the number of topics that could have been covered in addition to what is already on there, I would have been fine with the book being longer.
Overall, I give this book a 4.9 out of 5 stars. The author did an excellent job writing this book. I can find little fault.
The first chapters introduce basic of Python library Keras via TensorFlow API as a tool for building models architectures. Concepts of such as regularisation, regularisation, performance evaluation, model structures are presented in a way that both novice and a Deep Learning practitioners would find valuable.
There is a clear flow of ideas as the author moves from basics to advance models building. This book could have been longer. Natural Language Processing and Audio Processing are topics that are not covered. Nevertheless, what is covered is covered very well.