Deep Learning with TensorFlow and Keras: Build and deploy supervised, unsupervised, deep, and reinforcement learning models, 3rd Edition

Nearly 700 pages of indispensable references and examples on how to use two of the most popular and AI and ML libraries out there. I have just skimmed through it currently and was literally blown away at how many examples this book provides. To me having examples to follow when you are new to learning this stuff is essential and a must and this book does not lack in that department.As others have already mentioned it gives a great introduction on the subject and talks about what TensorFlow and Keras is and what these libraries are built for. It gets in depth into things like Regression and Classification models. CNN's, DCNN's, RNN's, GAN's, and a ton more!!!It has a dedicated chapter on just the math behind Deep Learning which is really amazing for all the big math buffs out there. I like it because it is not hard to follow and you can easily follow along to most of the book with very little math background which is why having libraries like TF and Keras is so powerful. It gives programmers a simple to use API that allows anyone with the desire to start working on their own projects the tools to do so without being bogged down by the difficult things which have been abstracted away to such a level that you can now run models with less then 100 lines of code. So amazing when you really think about it.This book not only provides easy to follow examples, and writing style, it has a ton of references for each chapter giving the reader the opportunity to follow up with anything they want to dig deeper into which is very powerful for finding additional information on the subjects. This is especially useful for students and researchers who are actively writing peer reviewed papers on this subject.I would recommend this book to anyone who is interested in learning about or anyone who may already be involved in AI and ML, or just anyone in general. You can know nothing and this book will be helpful to you or you can already be a seasoned expert and this book will still be valuable to you, it is just a well rounded and jam packed book full of useful examples and knowledge.I am very happy I picked this book up.

One of the best resources to learn the tricks of the trade of building cutting edge Machine and Deep Learning systems. Authors team has put in efforts to clearly explain the fundamentals of ML and DL. Extensive code samples are helpful for successful learning.This book provides just right theory and practice required to use Keras, TensorFlow, and AutoML to build machine learning systems....

A great reference; very light on pedagogy. The book contains an incredible amount of reference information but when new concepts or terms are introduced they are done so without explanation. A look at the index in response to this reveals that the index is very incomplete. Descriptions are given in detail for some things but use buzzwords that onlyan expert in that field would know. This, side by side explanations of terms more suited to someone who has notechnical background whatsoever. I am puzzled about who the books for but appreciate its breadth

Hello World 🌎!!!I am a STEM Learning Scientist. AI/IoT/MachineLearning-ML/DeepLearning-DL are the holy grail of STEM education in the digital economy. In this day and age it's very difficult to find curricula and pedagogical resources for these bleeding-edge Learning technologies. This is where this epic book comes in to save the day. The hands-on inquiry-based learning activities are a reference standard. This book is so well written and organized; it's also perfect for any hacker space/innovative STEM Hub/Classroom ...etc. If you're immersed or tinkering around in AI/IoT/MachineLearning-ML/DeepLearning-DL, I highly recommend you pick up a copy of this elegant book. Well done 👏!!!!!

The book is an applied, practical exploration of the concepts of deep learning. The authors start with what both TensorFlow and Keras. They then discuss and explain the various concepts of a neural network.The book examines several kinds of neural networks. Such as the perceptron, convolutional, recurrent, self-organizing, and others. The book covers the topics of supervised, unsupervised, transformers, and generative models. The authors also examine regression and classification. All in all the book covers a large domain of the area of machine learning with neural networks.The authors have an engaging and pleasant writing style that is easy to read. The Python source code interspersed so that the described idea then has example code. The concepts are then put into practice and application using Python source code. The Python source code used has enough commentary to explain what it does. Yet not commented so that it obscures the Python code.The Python source code is online at GitHub and is available for download. Even better there is a Discord channel for discussion of the book and its concepts.I would give this book a grade of an A-minus. The text is very well written, organized, and constructed. The book is a practical how-to for learning and tinkering with deep learning.The authors show and tell the concept and code. Yet what might also add is the authors' suggestions for the reader to experiment. Give a “what if?” problem or idea, and then let the reader explore using TensorFlow and Keras. This would also encourage discussion on the Discord channels.Another issue is that there are many topics in the book. A helpful guide for using the book is a flowchart. The flowchart with an explanation from the authors on reading order. This would give a "roadmap" of chapters are then organized for how the reader wants to proceed.The book has a chapter that delves into mathematics for deep learning, which is a useful resource. Yet, this chapter on mathematics is better as an appendix at the end of the book.Understanding the mathematics used in a deep learning neural network is important. Yet it is an unexpected tangent in the different chapters. Hence moving this chapter as an end-of-the-book appendix. This avoids an unexpected "bump" in the chapters that examine neural networks.There are some minor issues with the book. Nonetheless, this is a book I recommend for learning machine learning. With some adjustments, the book then will go from a great book to an awesome book. The book is both for the newb learner, or a student in a university class.