And Techniques to Build Intelligent Systems

Excellent book. Gives the foundation of ML very well. He even includes other books to read along with his. I would suggest reading this along with Sebastian rashkas book, a book on introduction to statistical learning.

This book is very well written and comprehensive. I enjoyed how it covered a lot of the theory of ML in easy to understand language and simple math. The explanations enabled me to be able to visualize a lot of concepts like regularization and cross validation and SVM that I didn't intuitively capture solely from the formulas. The book was very smooth in working though the python code step by step at the same time as explaining the theory and how each concept it used.

I appreciated the books message that understanding the input data and having a good grasp on under/overfitting issues is a lot more important than which new magic formula one is plugging in.

One thing.. there are gazillions of books and courses out there for learning ML and playing around with data analysis, so many nice demos in jupyter notebooks, but very very little on how ML can be used commercially. If anyone has any suggestions learning material on how ML is put into a production webserver and/or how real world data is used in a realtime system please let me know.

Simply the best way for Pythonistas to learn Machine Learning. This book covers the two main machine learning libraries in Python (scikit-learn and TensorFlow).

The book is extremely well written and easy for a beginner to follow. The first half of the book walks you through a machine learning projects and explains how to apply "traditional" machine learning algorithms using the scikit-learn library.

The second half of the book dives into modern deep neural networks. It includes a detailed introduction to the TensorFlow library, and demonstrates how to use TensorFlow to develop image recognition software, natural language processors, autoencoders and reinforcement learning models.

This book has one of the highest educational values I have seen in a book in a long time. I wish more books followed this format of tackling a problem like you would in the real world.

It's very easy to follow and almost feels like I am doing an internship with a real data scientist at my side. Coming from this frame of mind allows me to associate the problem solving to how I would actually use it. There's useful tidbits through in as well that you normally wouldn't get in books that cover things topically or by software feature.

Concepts are gradually introduced and everything is easy to follow without a heavy math background.

Has pretty good content with details, but not well-organized. You really need to spend time to read through the details to learn what you need to learn. Should not have started with neural network. Could be written in a more compact and easier way without putting unnecessary details. Had a hard time to trace back useful information after reading past several chapters, using bookmarks all over.

Overall, it really is superb. I know one other commented on - or complained about - it being a black & white print. Indeed, it surprisingly is, though it's nonissue for 90% of the visuals but for those that use a colorbar (such as heatmaps) esp. with a bimodal gradient (where the middle would be white, ends black), representation of the dimension is, well, compromised. Yet I can't even dock one star for that -- it's just too good of a text on all other accounts.

This book is way better to read than the Goodfellow book. It introduces concepts in clearer and easy to understand text compared to the other. If you're a practitioner and you just want to learn the standard practices and occasionally how to improve your ML performance using state of art tools such as Tensorflow, you should pick this one. If you're a researcher in this community and you want to grow more theoretical thinking out of it, the you should choose the other one.
My use case is to get a ramp up for RNN and tensorflow and I found it doable just in a couple of days

I purchased the kindle version of this book. I have had it for about 10 days.

This book has the quality and utility I expect from O'Reilly titles. There is a mix of theory and example I prefer and when learning new topics, and I have always found these titles provide a quick entry into a new topic. The author is very knowledgeable and covers a lot of material. This book has a better combination of breadth and depth than most O'Reilly titles. Different methods and approaches are described in greater detail than usually found in these books. I feel I have benefitted from the author's knowledge and experience in applying ML techniques to a wide variety of problems. He also provides a rich set of links and references for further study. Very happy with this purchase and I highly recommend the book.

The writing is good and understandable. However, I have couple of remarks. There are some chapters that promise to dive in into technical details, but all of them ultimately fail to give enough theoretical background.
Also, criticism to a publisher. The book copy I have obtained have a lot of pages with empty plots.

This is too good a book. However the author first gets your hand dirty in the in the first chapter, however, he will explain what's under the hood from the third chapter onward. His advice is very succinct and extremely practical. The way he explained learning rate, regularization etc is excellent actually bare minimum one needs to know.

However, it's not a book for an "absolute" beginner. But if you have a little bit of familiarity with few of the terms or jargons, you're good to go. This is one of the books one must have in their shelf if they want to call themselves a Data Scientist or ML/AI researcher.

The book teaches you how to use libraries, instead of building from scratch. I'm very surprised this book has such a high rating. Since this book I have read many better books that get the point across.

Good book, really interesting for tensorflow. my best friend is a practitioner of ML and told me the first part was ful of great details. I skipped it, using rather S. Rashka books for that, but TF is really well explained

Very nice book. The author former googler had strong theoretical background and extensive practical experience on ML. The contents are well presented. The well-organized detailed jupyter notebook (free to download on github) adds extra bonus.

The author explains contents in the manner one would expect from a Hands-On book, however I've found several blank figures while browsing through the book and it's rather disappointing as I only had the opportunity to check the book after the return window closed :/

The Kindle version (Windows 10 on a 13" convertible notebook/table) render the page with every page turn; text and images change position so it can fit as much content as possible. This is annoying if you are searching for a text based on the position of an image or just turning a page back and forth to reread some text. Page numbers (14,621 Vs 574) do not match the hardcopy. However, with this approach, the font is very large and easy to read using an e-reader device. Pictures are colored compared to the paperback version. As an introductory machine learning textbook, the content is easy to understand, and step-by-step instructions are provided.

Great book to learn basics to intermediate Machine Learning. I have read several books like this since I work at a research lab and give talks about machine learning. The examples of this book are really good and the way it teaches the concepts make it much easier to learn.

This book is just awesome. The explanation on concepts are clear, and the example codes are pretty concise and exploit the advantage of original frameworks. I realized that I still need books while there are plethora of free articles and tutorials on the web.

An amazing reference which packs up all what I needed to know about Machine Learning starting from simple linear regression till complex deep learning neural networks. It offers a lot of practical exercises with their answers published on github. It also relates the machine learning tasks to real life business domains.

I found this book really useful all main principals are very well explained and you can really learn something new from it whether you are just a beginer in machine learning or already know something. Highly recomend this book for everyone who are interested about machine learning.

This book has been the greatest resource I've found to learn machine learning. I have intermediate experience with Python and had only a basic understanding of Jupyter notebooks and scientific Python before opening this book, and it's been an awesome experience.
This book is:
- clearly written
- teaches you machine learning through projects rather than jargon
- contains a lot of personality (As quoted in a note, "You will often see people set the random seed to 42. This number has no special property, other than to be The Answer to the Ultimate Question of Life, the Universe, and Everything.")
- contains exercises at the end of each chapter to recap what you learned

This is by no means an exhaustive resource to scientific Python or machine learning, but I've obtained a lot of insight into the methodologies of a data scientist, as well as seeing Pandas methods put into action. Aurélien will provide you a basic understanding of some of the things he does, but it is up to you to use the docs if you want to see the power of some of the methods. With all the things you can do in matplotlib, pandas, numpy, and sci-kit learn, I appreciate seeing them in action, then doing research on them myself rather than sifting through docs to see what methods, functions, or attributes I can use.

I have yet to reach the section on TensorFlow, but I'll give an update when I get there. Also, don't be intimidated by the length of this book, it's NOT a textbook.

I am very much a machine learning novice although with a technical background much of the math with its focus on linear algebra and probability and statistics is familiar. I have purchased several other ML books in the past year and have found some better than others. This new book I really like. I downloaded the sample first chapter which is length and a great read and I knew the authors writing style and combination of theory (without a lot of equations) and practice (the hands-on) via Python was just right to encourage me to purchase and read the rest of this book. I am already well into Chapter 3 and I am still very much enjoying this book. Besides the focus on Scikit-Learn, a novel and timely focus in the later part of the book on TensorFlow makes this book a must have if you want to be current. There are a few other titles out there on Deep Learning and TensorFlow but I have not found one that includes an introduce to ML, as well as DL, and these two key Python-based software tools. I definitely recommmend this book as a must have!

The content is very good. However, the actual paperback print is very poor. First of all it's not in color, rendering some of the plots useless (e.g. clustering by color). The quality of paper is also newspaper like - feels cheap, dirty, and easy to rip. Some pages were also a bit dirty too. Returning my purchase.