Hands-On Machine Learning with Scikit-Learn and Tensor Flow: Concepts, Tools, and Techniques to Build Intelligent Systems

This book takes a different approach to teaching ML. Instead of focusing on just concepts, practical hands-on experience is given more priority. Here are some of the pros and cons:Pros:1. Great laid out content.2. Example-based approach.3. Lots of projects to do.4. Teaches how to build a ML model instead of focusing on the underlying concepts only.Cons:1. Little short of concepts, actually.This book serves a great deal. But still you should know about Py-dependencies like NumPy, Pandas, Matplotlib etc. which are explained in O'Reilly's Data Science Handbook quite well.To learn python, I would suggest going for free resources at Udacity, CodeAcademy or even some of O'Reilly's free eBooks.Sometimes you might not understand a particular implementation. In those cases having a little conceptual background helps. I suggest going for Ian Goodfellow's Deep Learning book which can be grabbed for nothing from GitHub. This book explains the concepts immensely well.Thank You.

Tha book is all what one needs to be confident to pursue analytics journey.Having spent years in the analytics industry, I find the book good for a person with some elementary know how of Machine learning like regression, Decision Trees.Part 1 of the book is good for beginners to make their knowledge concrete on the basiscs of Machine learning algos.Part 2 is more advanced stuff and talks about Neural nets ( different types) and dee learning.One gets to do analysis on datasets with codes , to get the right feel of an analytics project.A good book for anyone looking to get ahead..

This book is probably the best introduction for Machine Learning frameworks for some looking to apply it in their daily work or just as a hobby. Its not an academic textbook at all as focus on proofs and theory is left for exploration. Its mostly a guided tour with important things to remember about each ML algorithm.The addition of exercises at the end of each chapter is a welcome feature as it really tests your understanding. If you are familiar with Python then this is probably the first ML book to learn. Good luck!NOTE ON INDIAN EDITION: The printing quality is abysmal and really disappointing. Color printing would have been very useful as most of the charts are comparisons and would help in visualizing tuning of hyperparameters etc. Get the US edition if you can spare the change.

Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems This is one of the best books you can get for someone who is just starting out in ML, in its libraries such as Tensorflow, It covers the basics very good. As a book, it is 5/5Once you are done with this book, the ideal next step is the "Deep Learning Book By Ian Goodfellow".Sadly my copy didn't look so good, If it were an under 300 book, I would have let it slide but when the book costs 1450 (Which it is totally worth it) I expected a much better copy.

I would recommend the users to wait for second edition of this book. The Keras has become default API for Tensorflow 2 and many features like placeholders , initializers , variables etc have become redundant. However this book is a masterpiece because it teaches you lot of practical applications with a substantial theory.

One of the best books I've read on the topic. The right mix of theory and programming.The breadth could've been better. Nevertheless, great book. Lucid explanations.- Coming from an ML practitioner and someone who has read 20+ books on the ML.

Quick glance shows that subject covered is done with just the right amount of focus on basics vs hands-on ML.Quite simply written and not intimidating at all. For those looking for a very deep look into the basics and the math background of the concepts should probably check out Duke University’s machine learning mastery with excel - which is a rigorous crash course on the very basics of the math.The problem with book quality on amazon is hit or miss. Paper that it’s published on is slightly cheap quality.Looks like also someone has used the book. That may be a concern to some people.

Great book for beginners. If you want a great introduction along with the practical knowledge on Machine Learning, I suggest you look further, think no longer and just buy this book. Believe me, this will be one of the best purchases you've ever done.

I bought a few other machine learning books before, and this one is by far the best. It is very thorough, and extremely clear. It covers everything I was hoping to learn: convolutional neural networks, deep reinforcement learning, recurrent nets, and it clarified a lot of things I thought I already knew: random forests, ensemble learning, svms and so on.There's a ton of great figures and graphs, it's easy to read and the author is clearly knowledgeable. I like the fact that there's pointers to the original papers everywhere. All the code examples are on github, and there are many exercises (I only did the tensorflow ones, but they were great). Very "hands on", like the title says.

Es uno de los mejores libros que he encontrado para machine learning. Se lee bien, es fácil de entender, y puedes ir siguiendo el código paso a paso. Muy recomendable

This book is a wonderful introduction to Machine Learning, with easy to follow examples and great explanation of the concepts involved.It's divided into two parts, the first deals with "classical" machine learning using scikit-learn which is my favorite part of the book. The second part deals with (deep) neural networks using Tensorflow. It explains the concepts well, but I liked it a lot less than the first part. I read it cover to cover in the kindle version (very practical together with the web-based kindle app and the jupyter notebooks). I will also buy the printed version to keep for reference later on (too bad that Amazon doesn't offer a discount to people who wish to buy both versions).All in all very recommended!

me gusta, el libro está muy bien y toca muchos aspectos de Deep learning con bastante profundidad, me hubiera gustado que hiciese una entrada más "suave" pero lo cierto es que enseguida se mete en profundidad en muchos conceptos que necesitan de estudio individual para poder asimilarlos bien. TensorFlow no es "instalar y usar", hay que tener un bagaje previo bastante grande para usarlo correctamente, no es como aprender de repente a programar en otro lenguaje, creo que las personas que realmente le sacan partido invierten el 100% de su jornada laboral en estos temas.

Good book to get started in ML