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

While I enjoy learning from this book, the math font in kindle edition is a mess which makes the reading unpleasant. I know to some this probably shouldn't be a deal breaker but for someone who wants to move from hard copy to kindle, it was a disappointment.

I've read all of the predominant machine learning related python books and this one is by far the best one. I was excited to see the second edition of this book come out. It is packed with new information (1.5x the length of the first edition) and updated for TensorFlow 2. I have the Kindle edition and find it very helpful to highlight key points. I look forward to receiving the print edition as well once it is released. EDIT: Just received the print edition of the book and it's in color! The first edition wasn't. This is a pleasant surprise as it makes it easier to read with various charts and graphics.

This is an update for my previous review. Recently, I gave one star for the poor ebook experience but with author's comment I realized the publisher updated the ebook and now everything is great in the ebook. As the name suggests, the book gives you a really hands-on experience on machine learning. This covers most of the recent main advancements in the field.

This book gives you a hands-on approach to learning by doing. As opposed to the trendy deep learning books that dive deep into the weeds from the start, this book starts with the more traditional ML approaches (the Scikit-learn part) giving you a great deal of context and practical tools for solving all kinds of problems. Only after does he transition into deep learning concepts, giving you both a great overview and the background to understand when and where to apply the various techniques. Its code-focused so you'll have the option to run working code on real problems throughout the book. Most important for me, he focuses on explanation over hand-wavy equations that are rampant in other ML books. I say hand-wavy because they typically go like so: "Here's a hard concept. Rather than explain it well, I'll give you some linear algebra and calculus equations, remind you that this is stuff you should have learned in high school, and then move on." Authors probably feel justified in doing this, but after reading a book like this you understand what they are really doing: Skipping the hard-part of breaking difficult concepts down into chunks that can be consumed by a competent programmer, who is perhaps not an expert in "high school" math. Moreover, this author does so without dumbing down the content. That's the mark of someone who well understands both the content and the audience. This book is long and dense, and serves as both a guide and a reference. It is not a quick read / overview or light reading type book.

I'm very pleased with this book. I enjoy the little bits of humor here and there, and it does a great job not glossing over important details that might be a stumbling block for someone. I'm quite comfortable with python however I appreciated that he did go into depth on setting up virtual environments and best practices. I remember years back when I was starting that whole concept tripped me up so much, having this explained so well is going to save someone a lot of time. Also his code seems so far to be written in a very thoughtful way and has them all on github. He also goes into lots of gotchas and tips and tricks that just overall seem to add a certain maturity to his writing. He has obviously very well versed in machine learning. Overall I would recommend. It's been much more interesting than I expected.

Aurelien did it again! Whether you are a data scientist looking to start building predictive models in Python, or a software developer looking to become an ML engineer, look no further! The excellent balance between theory/background and implementation that was present in the first edition is kept, with the essential material additions made (e.g. the unsupervised learning in the "classical ML" part, or the Keras API, which is quickly becoming the most popular way to use TensorFlow). Needless to say, the Jupyter notes accompanying each chapter are more than helpful. Also, as a cherry on top, the illustrations in the printed version are now in color, which makes it even easier to read. In summary, this book is an absolute must-have for a Python-rooted data scientist / ML engineer!

The book was worth the wait! The publication quality of the print edition is great. Love the color illustrations. The one thing that I miss is that having bought the print edition, it would be sweet to have an offer to acquire the electronic edition at a reduced price but since Amazon now seems to be handling O'Reilly book sales and probably wants to sell as many Kindle editions as possible, a PDF copy of Hands-On Machine Learning, 2nd Ed., does not seem to be in my future at a bargain price. My review is preliminary - I've read bits of the online draft version-and the clarity and superb organization of Géron's writing convinced me that I wanted a finished copy of the book. My current avocational interest is Reinforcement Learning and Géron gives an excellent overview - to dive deep, one would probably still want to refer to Sutton & Barto's 2nd Ed. book (available on Amazon or for free online) or David Silver's excellent 2015 UCL lectures, also available online.. I will slowly work my way through Géron's book in its entirety but my primary reason for owning the book is as a reference. It makes a great roadmap to the current state of machine learning and, best of all, it makes learning about ML fun!

I'm finishing up an MCS in Data Science from UIUC and I can tell you bar none that this book should be required reading in this subject. The required ML course at school was so confusing and they assumed WAY too much. Reading over the same topics in this book was like night and day in terms of explaining things in a way that makes sense. The images, graphs, and tables are clear and help a lot by providing visuals to the text explanation. I did notice a few typos but so far nothing critical. This is not a light read as it comes in at almost 800 pages but taking it model-by-model is easy to do.

The Tokyo Olympics of 2020 got postponed to 2021. If there were a contest for best AI/ML book at the Olympics this year this book would have earned the gold medal ! I loved it so much that I read it at least twice, and each time I underlined/highlighted/took-notes. I love how lucidly the author explains concepts. He does an excellent job of explaining topics such as the model, the learning algorithm (also called the optimization algorithm), regularization hyperparameter, generalization etc. The examples are great and even if one does not know python programming it is easy to follow along. (I learned python a few months later, which made it even easier and more interesting to follow the examples in this and other books). While no one single book can teach one ML/AI, this book would make the Mount Rushmore of AI/ML books (along with (1) Intro to Statistical Learning by Hastie etc (2) Intro to Machine Learning by Alpaydin (3) Deep Learning by Goodfellow, Bengio etc). I highly recommend this book to anyone aspiring to get into the field of ML/AI.

This is the third book I've bought from this guy and every single time on the first coding example(and other examples) there are codes missing or he doesn't add codes that he has already spoken about, unlike the other books where he constantly repeats the same thing over and over but for some reason can seem to repeat the code. Sometimes he just forgets to put in a line of code. This book is free online I learned that after googling for the right code but still I prefer buying the book. Even so, he should really have someone else check his work. unlike the other books, he keeps up with where he puts his "imports" and "from" codes in his other books it was always where he starts using it which is bad coding those codes should be put at the top of all the line of codes for ease of finding and it was well structured for that I will give it three stars. Despite, having to look for missing code I did enjoy this book it did help to have resources from his other books. This isn't really a surprise because I've done it in college, but I did not expect to do it in the first example from a well-known author. If you're thinking of getting the book get it but only if you plan on using other resources that is if you are completely new to coding. I would like to add if it wasn't for StackOverflow and his community on GitHub I would have given it a one star. Just know once you get the code working you get the biggest satisfaction and you will keep pressing on. Good luck during this pandemic coders

While I enjoy learning from this book, the math font in kindle edition is a mess which makes the reading unpleasant. I know to some this probably shouldn't be a deal breaker but for someone who wants to move from hard copy to kindle, it was a disappointment.

I've read all of the predominant machine learning related python books and this one is by far the best one. I was excited to see the second edition of this book come out. It is packed with new information (1.5x the length of the first edition) and updated for TensorFlow 2. I have the Kindle edition and find it very helpful to highlight key points. I look forward to receiving the print edition as well once it is released. EDIT: Just received the print edition of the book and it's in color! The first edition wasn't. This is a pleasant surprise as it makes it easier to read with various charts and graphics.

This is an update for my previous review. Recently, I gave one star for the poor ebook experience but with author's comment I realized the publisher updated the ebook and now everything is great in the ebook. As the name suggests, the book gives you a really hands-on experience on machine learning. This covers most of the recent main advancements in the field.

This book gives you a hands-on approach to learning by doing. As opposed to the trendy deep learning books that dive deep into the weeds from the start, this book starts with the more traditional ML approaches (the Scikit-learn part) giving you a great deal of context and practical tools for solving all kinds of problems. Only after does he transition into deep learning concepts, giving you both a great overview and the background to understand when and where to apply the various techniques. Its code-focused so you'll have the option to run working code on real problems throughout the book. Most important for me, he focuses on explanation over hand-wavy equations that are rampant in other ML books. I say hand-wavy because they typically go like so: "Here's a hard concept. Rather than explain it well, I'll give you some linear algebra and calculus equations, remind you that this is stuff you should have learned in high school, and then move on." Authors probably feel justified in doing this, but after reading a book like this you understand what they are really doing: Skipping the hard-part of breaking difficult concepts down into chunks that can be consumed by a competent programmer, who is perhaps not an expert in "high school" math. Moreover, this author does so without dumbing down the content. That's the mark of someone who well understands both the content and the audience. This book is long and dense, and serves as both a guide and a reference. It is not a quick read / overview or light reading type book.

I'm very pleased with this book. I enjoy the little bits of humor here and there, and it does a great job not glossing over important details that might be a stumbling block for someone. I'm quite comfortable with python however I appreciated that he did go into depth on setting up virtual environments and best practices. I remember years back when I was starting that whole concept tripped me up so much, having this explained so well is going to save someone a lot of time. Also his code seems so far to be written in a very thoughtful way and has them all on github. He also goes into lots of gotchas and tips and tricks that just overall seem to add a certain maturity to his writing. He has obviously very well versed in machine learning. Overall I would recommend. It's been much more interesting than I expected.

Aurelien did it again! Whether you are a data scientist looking to start building predictive models in Python, or a software developer looking to become an ML engineer, look no further! The excellent balance between theory/background and implementation that was present in the first edition is kept, with the essential material additions made (e.g. the unsupervised learning in the "classical ML" part, or the Keras API, which is quickly becoming the most popular way to use TensorFlow). Needless to say, the Jupyter notes accompanying each chapter are more than helpful. Also, as a cherry on top, the illustrations in the printed version are now in color, which makes it even easier to read. In summary, this book is an absolute must-have for a Python-rooted data scientist / ML engineer!

The book was worth the wait! The publication quality of the print edition is great. Love the color illustrations. The one thing that I miss is that having bought the print edition, it would be sweet to have an offer to acquire the electronic edition at a reduced price but since Amazon now seems to be handling O'Reilly book sales and probably wants to sell as many Kindle editions as possible, a PDF copy of Hands-On Machine Learning, 2nd Ed., does not seem to be in my future at a bargain price. My review is preliminary - I've read bits of the online draft version-and the clarity and superb organization of Géron's writing convinced me that I wanted a finished copy of the book. My current avocational interest is Reinforcement Learning and Géron gives an excellent overview - to dive deep, one would probably still want to refer to Sutton & Barto's 2nd Ed. book (available on Amazon or for free online) or David Silver's excellent 2015 UCL lectures, also available online.. I will slowly work my way through Géron's book in its entirety but my primary reason for owning the book is as a reference. It makes a great roadmap to the current state of machine learning and, best of all, it makes learning about ML fun!

I'm finishing up an MCS in Data Science from UIUC and I can tell you bar none that this book should be required reading in this subject. The required ML course at school was so confusing and they assumed WAY too much. Reading over the same topics in this book was like night and day in terms of explaining things in a way that makes sense. The images, graphs, and tables are clear and help a lot by providing visuals to the text explanation. I did notice a few typos but so far nothing critical. This is not a light read as it comes in at almost 800 pages but taking it model-by-model is easy to do.

The Tokyo Olympics of 2020 got postponed to 2021. If there were a contest for best AI/ML book at the Olympics this year this book would have earned the gold medal ! I loved it so much that I read it at least twice, and each time I underlined/highlighted/took-notes. I love how lucidly the author explains concepts. He does an excellent job of explaining topics such as the model, the learning algorithm (also called the optimization algorithm), regularization hyperparameter, generalization etc. The examples are great and even if one does not know python programming it is easy to follow along. (I learned python a few months later, which made it even easier and more interesting to follow the examples in this and other books). While no one single book can teach one ML/AI, this book would make the Mount Rushmore of AI/ML books (along with (1) Intro to Statistical Learning by Hastie etc (2) Intro to Machine Learning by Alpaydin (3) Deep Learning by Goodfellow, Bengio etc). I highly recommend this book to anyone aspiring to get into the field of ML/AI.

This is the third book I've bought from this guy and every single time on the first coding example(and other examples) there are codes missing or he doesn't add codes that he has already spoken about, unlike the other books where he constantly repeats the same thing over and over but for some reason can seem to repeat the code. Sometimes he just forgets to put in a line of code. This book is free online I learned that after googling for the right code but still I prefer buying the book. Even so, he should really have someone else check his work. unlike the other books, he keeps up with where he puts his "imports" and "from" codes in his other books it was always where he starts using it which is bad coding those codes should be put at the top of all the line of codes for ease of finding and it was well structured for that I will give it three stars. Despite, having to look for missing code I did enjoy this book it did help to have resources from his other books. This isn't really a surprise because I've done it in college, but I did not expect to do it in the first example from a well-known author. If you're thinking of getting the book get it but only if you plan on using other resources that is if you are completely new to coding. I would like to add if it wasn't for StackOverflow and his community on GitHub I would have given it a one star. Just know once you get the code working you get the biggest satisfaction and you will keep pressing on. Good luck during this pandemic coders

pros: - paper and overall quality cons: - right pages are printed with a slight disalignment, it’s not a big of a deal, but a little annoying. See attached pictures

I am only in the early chapters so far, but I noticed that it is very well written. It helps that this is a 2nd edition. ML concepts are not easy to explain clearly, so the author has done a fine job. Part 2 deep learning seems totally new to the 2nd edition. I was mostly interested in deep learning and was almost going to skip part 1, but am glad I didn’t. I am getting a concise review of basic ML in part 1. Re Kindle version, I am happy to report that the formatting works well. Code is easy to read and math formulas show up well. There is also color in graphs. O’Reilly print books are only in black and white and some graphs can’t be read because all lines or dots are the same black color. No problem here. I was able to get Alexa to read the book to me in a very realistic voice. I used iPad pro, installed Alexa app on it, then from the Alexa app, I opened the Kindle book, choose chapter, and pressed play. Alexa correctly pronounced scikit-learn, which is an achievement. Speech engine seems much improved and sounds very good. Connected a bluetooth headset. forward, back, pause, resume buttons on headset works.

The book begins with a short general discussion of machine learning, including data preparation, visualization, splitting into train and test sets, model fitting, and evaluation. The bulk of the book focuses on the techniques that are the current state-of-the-art -- ensembles and particularly deep learning. There is enough math to be convincing, but not so much to distract from practical applications. The sections describing deep learning architectures are particularly well done. Throughout the book, clear illustrations and fully disclosed Python 3 code enable the reader to replicate the author's work.

-I've already spent several tens of hours with this book. The Kindle version is (I consider) overly expensive considering the number of issues. -Many of the notebooks and/or book code examples do not work and/or take inordinate amounts of time to compute. -I can't count the number of times I've already had to go off and spend an hour or more updating or changing code so that it works, whether it be from the book or from the latest notebooks (which the author claims to keep up to date). -Explanations are often poor. For instance, when discussing false positives, false negatives, etc... He could have just put all definitions in one place, like on wikipedia, but instead he tries to "word" everything out. It's not a very methodical way of instruction. -Another python book with so many breaking inter-dependencies that it boggles the mind - yet the author implies that "from the ground up" solutions are just "toys." Well, at least those toys will not break down when some part of your byzantine collection of libraries is updated.

This is the best book you can buy if you want to implement machine learning to your project. What I really like about this is a book is that the author knows how to explain ML concepts by solving a real-world example problem, as opposed to just explaining the theory. Strong MATH knowledge isn't required to understand this book(just the basic and you can learn the concept as you go), however, strong programming knowledge is required based on my personal experience.

I am only about to start with chapter 4 but if the rest of the book is of the same quality as the first few chapters then it definitely deserves 5 stars. The title of the book covers the content, and the book comes loaded with practical advice as well as working code samples. In fact is comes with complete projects in the form of Jupyter Notebooks. You really cannot go wrong buying this book, certainly given the price. Even if there are some chapters you end up liking less then it's still worth the money. One heads up is that it's not an easy read. That is partly because of the nature of the material, and partly because the author thankfully goes into the technical details of the what and how (and does so in a very accessible way). There is no "handwaving"! As a result the text is a bit dense and it can make for slow reading, but on the other hand it then leaves you with the satisfaction of a rather good understanding of the topic. One more thing - it probably does not hurt to be well versed in Pandas, especially matrix-wide operations in a single line of code.

I’ve been kicking the ML learning can down the road for a while now. I’ve bought books in the past, but nothing really stuck as they get crazy theoretical by page 4. This book assumes very little ML knowledge, which describes me perfectly. Bought this book and can’t put it down. I’m on page 47 and keep peeking ahead to see what’s next. Best technical book I have purchased in many many years. Looking through all the content it amazes me how someone could present ALL this info in a format I get. Love it, totally recommend it. Thank you for this.

I bought the book from vendor Globalmart Online Shop, quality is very bad. Pages are cheap, looks like a printed copy, not original text book. I bought book from amazon (same version) first time around June this year (spoiled due to pet) is very good in terms of quality. Thickness and color of pages are very different and page alignment is different as well. I did put exchange of the book, if I get the same quality again, I will make sure to attach the photos and complain to Amazon on this vendor for cheating.

If you are looking to learning more about Data Science I highly recommend this book. The only stipulation is that if you have not used math or statistics for a couple years that you read "Practical Statistics for Data Scientists" first, or you may be a little lost. While this is an introduction to Machine Learning, it is not an introduction to Python, Linear Algebra, Calculus, or Statistics. You can still follow along with the code and science explanations, but if you are novice in math or programming just be ready to spend a couple hours researching a single paragraph from this book. This is not a bad thing and actually a strength of this book. Once you understand the fundamental concepts, the author concisely and accurately shows you how to implement the model. HIGHLY RECOMMEND!!!!

This book is a gem! I have read many textbooks and this is one of those books that is interesting, informative and well structured and includes so many great details. The book is meant more for practitioners but there is still enough math and lots of references to papers if the reader wants more theoretical information. I would recommend this book to anyone whether you are an undergrad or a PhD with several years of experience. Truly a well written book ! Thank you Aurelion !

A nice educational, very well written and up to date overview of machine learning techniques + tons of practical and well documented code in python that can be used straight out of the box. Lot's of stuff is in there. A lot of the of the book is spent on neural networks including the latest and greatest varieties. Just check out the table of context. There are tons of high quality and informative graphics in the book, all in color, plus colored syntax highlighting. So far i have not seen any other book with colored syntax highlighting.

This is an excellent book for an introduction to Keras and Tensorflow. It complements the Coursera Tensorflow course and the tutorials on the Tensorflow website very well. At first, I didn’t appreciate that the first half of the book is devoted to machine learning. But after reading that part, I learnt many new tricks/shortcuts. For example, how easy it is to do stratified shuffle spits to balance out the training and test samples and creating pipelines. The book also reenforces a process for ML, which I really liked. The deep learning part of the book is excellent as well. It has the right balance between theory and practical ways to use Tensorflow. Having the code available on Github is very helpful. The book is easy to read and to understand (a fairly complex topic). It is an invaluable resource!

I've read about 90 pages and am impressed by thoroughly various topics are covered. You can eventually learn all of this by reading multiple other books but it is much better to have all of the info well- organized in one place. I am not a subject matter expert but so far I like this book much better than the Manning series which I have bought several of.

I took a machine learning graduate course in my master program. I had a top conference paper. The professor used 1st edition of this book as one textbook for the course. I had a 1st edition of the book but did not have time to read. Now I buy the 2nd edition because the Tensorflow 2 has merged with Keras, which means we can avoid to learn the hard syntax of tensorflow 1.0, and there are a lot of new advances in machine learning, such as generative models. Also to my surprise, the book is colorful. That makes the book is more interesting. Each chapter has summary of math. That is better than some programming machine learning books that do not have any math. If you have some backgrounds in math of machine learning, this book can save you time because it gives you the whole picture without lost. If you are very interested in some equations and want to derive them, you can use Pattern Recognition and Machine Learning book. The Github has a lot of python projects of machine learning. The codes are well-written. If you can write codes like the codes in the projects, you will have the potential to enter Google. Go Google, the book is a must have.

I am using the kindle app on my ipad to view this book. However, some of the equations are just very unattractive due to the sizing issues... I gave up and decided to go back to a physical book. It would be great if this is fixed... Other people have also voiced similar concerns back last year and it's still not fixed

I purchased this book a while back before attending a 3-month on-site bootcamp program with a capstone project. After graduating the program and before starting my job as a ML scientist, I found time to read this book and I must say it is an investment worth its price. Even though I had the best teachers in the bootcamp, it was very hands-on and some concepts got lost or rushed due to time constraints. This book is the first reference book that I do not get bored of, it does NOT have a dry language and flows perfectly. I am just reading it and even that suffices; I am sure doing the hand-on exercises will make it better. I now understood theoretical concepts and got a hold on why we used some parameters in a given way. I highly suggest it to everyone who wants to delve into this world.

This book is a perfect addition to any theoretical ML advanced course where an instructor can introduce theoretical math. concepts of ML based on statistical learning or/and optimization theory and use this book as a good set of examples with ready to use well explained codes. Really good job thank you for your book.

This is one of the books every good data scientist has to have. Everyone and his mother is calling himself a “Data Scientist” and they have no practical experience, no math background, and no conception of how to use data science. This book solves a lot of those problems or at least you can spot the phonies. It is one of the best data science books ever written.

Upgraded from the First Edition to the Second. Great resource for in-depth explanations, or if you use it as a reference "Cookbook." As an added plus, the author posts all his code/examples on GitHub for everyone to access.

I would recommend this book as the primary source for machine learning with Python and Tensorflow 2. Pros: Among all the books on TensorFlow 2 this one is definitely the best. The second part (Neural Networks) goes much deeper into tf.keras than any other textbook I could find. Cons: Many important details are either missing or just glossed over. The code samples are riddled with mistakes and typos.

After a delay in my shipment and opening the package, I am extremely disappointed. I really was excited to read this book too, but I can't. The quality of the book is not new. It looks used, beaten and some of the pages are not even binded, heck some of the pages are not even printed! It looks like someone even cut one of the edges somehow when failing to bind the page. It looks like someone noticed how trash the ink was and tried printing over the old page only to end up making it look worse. I cant even read this, how could someone sell this and think this is "new"??

Aurélien Géron is a skilled writer and teacher. If statistical analysis is not your thing, Géron walks you through machine learning with clear examples and ample explanations. If you’re an ML wizard, all the equations and TensorFlow code are there. I work with computational linguistics. Géron takes you from the basics of machine translation to the latest in transformer networks. This excellent book is well worth the price.

I am a newbie to ML, and have been self learing for last six months from online resources, and always considered a book as I like reading books. Thid is good book, and good exercise. I am on chapter 8 so far and liking it.

The content of the book seems pretty good, although I have not gone thoroughly through it. However, the quality of the printing is not satisfactory. In just a quick first inspection I found many blurry pages throughout the book, including figures, and at least 5 pages that were not printed at all, just like that, with the corresponding scripts and pieces of information missing. I tend to buy less books through Amazon day by day, since the quality of books leaves me almost 100% of the times dissapointed.

I am new to ML and so pleased to start my journey with this book. The book is well structured, content is great and it is aptly supported by up to date github repo. So far, I have just worked through the first half of it but can’t wait to finish cover to cover. If you want a good grasp on fundamentals, this is a great book to start with. It is by no means a book for beginners only, but a book that would definitely serve as a reference for years of ML journey.

Wonderful book! Just what I expected. Very practical, hands-on like the title says. I have the first edition and I don’t regret one single bit buying the second. A must for any machine learning practitioner!

The math in this class could be easier to read since machine learning is so math dependent. I'm lucky that I took a linear algebra class as well as statistics before taking the class or using this textbook, so that makes it much more accessible to me but, imagine that those without any recent math exposure this book will be harder to read. So far it is the only drawback that I have seen. Otherwise this book does a very very good job at explaining the topics and I find it a joy to read.

Compared to other TF related book this one teaches you all the whys instead of just listing the code to do tasks. It would great benefit you when working on your own projects. One thing I want to mention is that starting with Pytorch to see all the autograd in a "lower-level" building blocks made it easier for me to understand TF and its usage. So I figure it could be useful too learn both :-)

I used this book in a college course and found it was useful for learning the basics. I purchased this product as a gift for friend who was interested in learning more about ML.

the best book of machine learning in python, i said that for the suggest that give us

Excellent book to get into the most popular libraries for machine learning using python. Good examples and support.

Great book that provides an appropriate amount of theory but is mostly focused on actually implementing the code. Would highly recommend for anyone who is interested in machine learning and data science.

*While some detailed/specific info is very dispersed within the book (It's a BIG book), it is natural due to the broad topics it covers. Hands on as the title promotes. Recommended if you can't wait to start programming artificial NN of several types in Python. *arrived with no flaws even before expected arrival time

This is exactly what I needed. Good examples and working code to go with it. I’m not through the whole book yet (not even close) and already have new methods I can use immediately. Very impressed and I highly recommend.

The actual information presented in this textbook is very insightful and I am thoroughly enjoying it. However that said, I am only on chapter 3 (not very far at all and have not been handling the book extensively), and part of the Index has simply fallen out. I can see strings attached to it, but it looks almost like the strings weren't bound correctly and it was just glue holding it on which seems to have been very poor. So I like the author, not such a fan of the printer.

I ordered this book accidentally (instead of fastai+pytorch book) and started looking through it. It has been a great read and resource. Just the right level of depth.

I am completely and utterly speechless in the presence of this work of art. I truly appreciate the effort put into it. This is THE BOOK for machine learning enthusiasts, PERIOD.

The examples in the book are really good and easy to follow. I have been using this as a reference for my project. It’s worth every penny!

I tried a couple of books on the topic but this one was hands down the easiest to understand. Definietly worth the price!

I recommend this book to anyone wanting to learn machine learning (ML) or working in the field, especially those without formal ML training like me. I read the book as a companion while taking an online course, then worked through some of the snippets in preparation for a certification exam. I am now using it for teaching and in practice. It's an excellent resource and I can't recommend highly enough!

A must read that's rounded out the education I received from school and has been great reference material ever since.

A classic. Clearly demarcated to sklearn based non-deep learning ML section and the deep learning portion which goes in-depth into Keras and tf. A good amount of material on deep reinforcement learning as well.

I love the way this book is organized, and how it outlines a framework for working through ML.

If you want to learn about Machine Learning of Zero, you have to read this book. I have read its first chapter and I can see excellent explanations and very clear content with pictures in colors.

The content of the book is very good, one of the best books in Machine Learning. Sadly, my order had a harsh travel, I suppose that got damaged on their way (see the pictures). I would appreciate better packing as it only has the bag with little bubbles (bubble mailers). I don't want to return it as delivery takes some time to this part of the world.

It's a beautiful book written with simple language and cute graphics. It's not repulsive like other books that try to throw readers into the abyss of intellectual jargon and make study boring intentionally. Also, the notebooks attached are good and helpful

It is an excellent presentation, though, a little verbose of an emerging area. Anyone entering into CS job market should be familiar with this book and the topics that are developed in detail.

Rich

The book arrived on time, however it was slightly torn at the bottom as shown in the picture.

Its quality is ok, but I think it is too expensive

I received the book in great condition. No any abnormal thing in it. I take quick view on it and it’s great and full of information and details. I recommend it for who want to learn ML

Great book with great updates for TF.Keras Highly recommended

Superb it is, in the method of teaching, in addition to very update content.

Coming from a SDE/SWE background, I used it as a “textbook“ to get into ML. Really comprehensive and easy to follow.

Highlighting items in this book and many books on Kindle in the last year has been a challenge to say the least. Highlights are on only for an instant and then unhighlight. This makes e reading impractical and as result I have stopped buying books on Kindle for which I need to highlight.

One of the best written deep learning books I’ve ever read. Simple to follow. Easy language even for beginners. A four star because at the time of purchase seller quoted a discount on brand new copy but I ended up receiving a used copy. Second time this has happened to me on this platform.

It's such a pity to have such a good book so poorly printed. Some words only have half printed. Lots of words and figs have a blur feeling. Kindle version may be better but kindle devices are just painful to use for learners.

I have read many books, this one is very good. Clear, details, hands-on approach. I recommend it 100%.

This book helped me immensely with understanding and using a lot of different kinds of machine learning models. Highly recommended!

Sample code seems to work well

I like the book presentation, very enjoyable, I use it to learn about Tensorflow.

No fancy review. I recommend it. Period.

Quick shipping. Exceptional condition for a used one. I’ve heard this is a great start to learn ML. I’m excited to read it

Damaged book received.

great book overall goes through all concepts in-depth and the math

The book a good organization and describes with colorful pictures

I am new to data science but it’s a lot less math heavier than I expected. It assumes you know most of the math to begin with. If you don’t know what you’re going to struggle. Other than that explains coding and concepts well

The most useful book I have ever read on any subject. The quality of the material is extraordinary.

The content is great The pages were not in order in the middle of the book. Please see photos Jumped from 324 to 340, descended in order to 325, then back up to 341

The pages are really thin and only 'fair' quality. Any worse and I would return. Content is great.

I just started Machine Learning and this is a very good book for anyone who's out there like me. I loved the content and organization. It's a get go kind of experience learning with this book.

Lo recomendamos para una lectura técnica y de aplicación en el área del análisis de Datos.

A nice combination of ML practice guidelines, source code, and ideas behind them.

Learn machine learning by practice, excellent book

Excelent book, congratulations to author!

Well written, intermediate level ML book.

I purchased the book 2 months ago and have slowly been making my way through it. When I got to page 100, I realized the next page was 229! This book is missing entire sections, would not recommend!

The contents of the book are incredible. But, the physical book is still emitting processing chemicals that are really distracting. The kind of smells that cheap magazines emit.

Really comprehensive. A+

Complete, clearly explained with good examples. It is a must.

Great content, great print. It's always on my work desk. Cannot count the number of times I refer to it! Good job!

Somany pages are missing and some pages are repeated. Author is really good but I am not happy with the publisher or seller. Not worth paying somuch. ☹️😓

I'm 100 pages into this book, and while the content is great, the formatting of the code snippets is atrocious. If you are thinking about the e-book, don't buy it, get the physical copy.

Very thoroughly written

Study preparation

I bought the book last week and it arrives on Tuesday. I can't wait to read it. However is there any advice on how to read the book top to down or down to top .? Thanks

It very detailed.

great book, lots of info

The examples are too complicated for beginners The theory is great

The book that I received was clearly used before.

This book is a must have. I will gladly be going through it a 2nd and 3rd time. Explains ML topics concisely and provides code to work along with.

Super in-depth snd informative

One of the best reference book for Tensorflow 2.0

Easy to read and follow, the content is of high quality, however the paper is too thin so you have to be very careful. Nevertheless is worth buying it.

I just started with ML (and I'll have to read the book a couple of times) but the author explains things really well. Exceptional work.

The product and the box are damaged and wrinkled!!!Disappointed!!!

Nice book

Good book on machine learning. The concepts get difficult very quick. Not for beginners.

Very great book on the topic!

De los mejores libros que he comprado para poder aprender en profundidad del tema.

Great examples

Lacks mathematical fundamentals, but overall is a good book.

I am finding this book to be very interesting and not boring like other ML books I had

the book’s paper is very thin. Doesn’t feel like o’reily quality.

Good book. Has a nice mix of theory and applications with step by step instructions. Now with figures in color.

I paid a premium for a new book but what arrived was dirty and had clearly been used.

Well written book well balanced between technical vs. being descriptive.

Go for that

Really nice book for practical machine learning

The title and photo say it all.

I liked that it is clear and it has practical examples.

One of the best books on ML out there

As described

My Top1 ML Textbook

This book is tough, no doubt. But after seeing dozens of online tutorials all geared towards absolute beginners, and 'code along' projects whereby the work is all but done for you it's refreshing to see a book like this. The information is incredibly thorough, isn't afraid to explain math, and perhaps most importantly this book unleashes you on many challenging open ended exercises in which you will truly be developing and demonstrating your competence with hands on open-ended projects. I'm so tired of learning resources that either have no exercises/projects or only have code along projects completely done for you in advance. This is one of the few sources I've seen that could reasonably make the claim that if you get through the material, and do all the exercises (without cheating and looking at the solutions), you will be well on your way to being competent practitioner of machine learning (if not already there). That said the prerequisites are no joke. You don't absolutely HAVE to understand the math but something is definitely lost if you don't. So you shouldn't be afraid of linear algebra, vector calculus, etc. (as an aside I believe it's one of the bigger problems of the machine learning/data science boom that many learning resources try to avoid math. the reality is that if you mindlessly call functions from libraries and and randomly fiddle with hyperparameters until something clicks, yes you can get some rudimentary results but you won't be as marketable or useful as you would be if you mathematically understood the process). Also this book is NOT for beginners of python. It's going to be very helpful to already have at least a rough understanding of classes, subclasses, object oriented programming, etc in the context of python as well as the obvious things such as loops, variables, if/then statements, lists, etc.

great

I have read around the library and buy many books about machine learning and find this book is the best one. I have finished almost all chapters of the 1st edition, and find the 2nd edition has enlarged to 850 pages, surely I order this new released one! It's really a nasty thing I cannot buy it directly from mainland of china.

As a statistician with limited experience in what the industry now calls 'data science', this book was the perfect translator. While nothing in the data science field is really all that new for anyone with a statistics, math, or economics background, the terminology and applications are slightly different. Fortunately this book will get you caught up to speed quickly. It is rich with detail (it is not a high level book meant for light reading. It's dense like a college textbook) and it complete with its explanations and python examples. The author was definitely very thorough (but concise!), and I want to thank him for his organization and editing. I'd recommend this book to anyone with advanced understanding of statistics (or statistical programming) wanting to learn the latest in data science applications.

Just have to throw in my two cents on the awesomeness of the printed edition. It's an 800 page book, and it's printed on bright white thinner and higher quality paper than most computer books (and most O'Reilly books for that matter). It has a nice flex/flow and weight to it and lays open pretty well. It just feels good in your hands and it's well constructed (unlike many recent $200 textbooks that seem specifically designed to fall apart within a semester to ruin their resale value). It's printed in full-color throughout. Honestly I think O'Reilly should start offering this quality of printing for more of their most popular books, even charging a bit extra for a "deluxe printing". I would pay another $5 for the books I use as frequent references. Anyhow, as to the book's content, I don't know of any better resource for going from neophyte to knowing at least the basics of most all of the latest ML architectures and applications. It's one of those rare books that doesn't tell you anything you don't need to know. All of the chapters are available as Python Jupyter Notebooks (without the majority of the chapter text of course), and they're ready to run on Google Colab for free so you can immediately start playing with any of the examples without needing anything more than a web browser and internet access. It doesn't get better!

It's amazing to me how this is the ONLY book of its kind, and it's the RIGHT book for a complete beginner in Machine Learning. Your prerequisites are Calculus and Python, that's it. The book demonstrates what Machine Learning is, how to do it, and offers explicit steps of EVERYTHING! Look, if you're going to perturb models, create new algorithms, or simply want a better understanding of the mathematics behind everything, you will need a strong foundation in Probability and Statistics (I recommend Larsen or Hogg), Linear Algebra, and Convex Optimization wouldn't hurt. You will then be able to tackle the "big girl" book, Elements of Statistical Learning (Hastie,Tibshirani,Freidman). Yet the point remains, that even after reading the latter, you STILL need to apply it, which means picking a programming language, become acquainted with the appropriate packages, and using it efficiently (yes it takes quite a bit of time to become familiar with all the shortcuts and optimizations). This is a great book and we should be grateful for the author's resources devoted to this valuable entity!

Arguably the best book out there on TensorFlow, Keras and ML in general. In fact, this is one of the most well written technical books I've ever read! No kidding! The code examples are very helpful. The author not only has a deep understanding of the material but also an outstanding technique for making it accessible. Too bad I can only give 5 stars.

It's hazardous to make as general a statement as "this is the best single book..." but I believe it holds true. This book manages to cover a broad range of important machine learning topics, yet with sufficient depth so as not to be superficial. The associated Jupyter notebooks are very well done, and they and the text complement each other nicely. I have a lot of machine learning books, but if I had to start over again with just one, this would be it. (Note: this review is based on the first edition, but glancing a the second edition, I believe it even more true.)

As a software engineer, this book really helps me develop a practical intuition about machine learning. The book introduces some of the theory behind algorithms, but more importantly, he digested the math theory part and outline the practical intuition and use case for each algorithm. After reading this book, I have a good understanding of why you would want to use a particular algorithm over one another, and what are the drawbacks of each and every one of them. While I do know the basic probability, linear algebra, and Calculus, I struggle with many other machine learning books as it tends to focus on the academic and theoretical part of Machine Learning. It's a must-read for any engineers looking to introduce Machine Learning into their projects.

This book picks the right level of detail, which is no small feat given the subject's breadth. It gives key intuition for the important concepts, often using good visual illustrations, but does not overwhelm the reader with details or method variations. I highly recommend it. (Note: other reviews warn that the Kindle version scrambles equations; the e-book version in the O'Reilly app does not have this problem.) For better insight into machine learning theory, read also "Learning from Data" by Yaser Abu-Mostafa (which Geron's book's intro also recommends).

Amazing and intuitive overview of the key ML concepts and developments! I've been studying ML since 2016, and I'm struck by how clear and insightful this book is! An interviewer first recommended this book to me -- and it has been the most valuable and cornerstone guide for me thus far! Clear sections, beautiful diagrams, and all diagram-generating code clearly available on a GitHub repo. This is a gold standard for ML instruction! Absolutely amazing!

This book is amazing, I love the tutorials in the GitHub as well. If you’re looking to buy the book, do yourself a favor and get the PDF version from ebooks.com. It’s more expensive but you can still get it in PDF format if you didn’t know. Kindle is a mess and it’s sort of shocking how Amazon doesn’t make more of an effort to improve Kindle for technical books.

This book covers tons in the field of machine learning. It is interesting in both the theory and actual implementation (mainly python and tensor-flow). Sometimes I get bogged down by the mathematics, but it has proven helpful for me to take side ventures of learning

It is not often that I comment on the books I read, but I felt compelled to do so in this case. I think this is one of the best books on ML/DL in the market. I wish I had had this book when I was starting off on ML.

This is a great book. Hits all the important topics as well as a lot of advanced ones and reads like a dream. I have checked out a lot of different texts over the years and this one is my favorite. It is comprehensive and all topics and source code are explained with the insight of a professional.

I'm relatively new to the world of Machine Learning and this book has taught me a lot in a very simple way.

I bought the 1st Edition. Now, there ought to be an easier/cheaper way to get the newer, 2nd Edition.

The best deep learning book ever !

Great balance of theory and practice.

All that you need to know if you're a Machine Learning beginner, from basic definitions and brief history, all the way up to reinforcement learning. Beside the intuitive and clear explanations, it also contains code snippets to help you get going with your own implementation. It's the best Machine Learning book I've read.

The book I received looks used and damaged :-(

After long time of waiting for the pre order, i finally got it. Love it!

If you have the budget to only buy one ML book, I would suggest going for this one. It covers most of the field in one book. Get a datacamo subscription too and you can break into the DS career.

I'm currently on a course learning Machine Learning and family and this book was recommended (well earlier revision), but it explains things well with good examples. I ordered on Kindle as much prefer reading that way Recommended if new to ML/DL/NN etc

This book was just released, and I'm only a few chapters into it, but I can already attest that it's an excellent approach to the topic. It reads like the book I would have written (or perhaps would have liked to have written) if I were to pen a volume on artificial intelligence. It's a long-overdue addition to the subject, and I'm thrilled to see it executed so well.

Good book about the machine learning and deep learning. with pratical codes using sklearn, tf2.0. but it is not easy to form a complete solution just from this book. It is worthy read a few times on some chapters to understand better. wonder any alternatives or complementary books...

It’s a colored book. Very well written with self-containing chapters, so you could either read from cover to cover or jump to the chapters most useful for you. Great for a wide knowledge range, either you don‘t know much about machine learning yet - this book would be a good starting point, or if you look for customize layers in neural networks, this book also talks about how to do that with subclassing Keras layers. It also mentions relevant papers for further reading.

This is an excellent book for machine learning, data science and deep learning. The print quality is great, the author's style of explaining concepts and going into enough depth of the subject is also amazing. I use this as my reference for any machine learning project. It is not just for beginners, it also teaches a lot of advanced concept including creating your custom models, optimisers and loss functions in Tensorflow. It goes from really basic machine learning modelling like linear or logistic regression to advance Deep Learning all the way to generative modelling. It assumes basic prior knowledge in python.

Great book, just what I was looking for. It's at exactly the right level for me. The author writes in a very straightforward, easy to understand way, but without oversimplifying. If you already know your way around python/pandas and jupyter notebooks, and have a decent grasp of linear algebra & stats (nothing beyond A-level standard), this is the book for you. I'm currently about half way through it, just getting into the neural networks stuff. Have started dabbling with kaggle as well. It's fascinating, and a lot of the concepts are actually pretty straightforward.

I received this book yesterday and am very impressed so far (currently on chapter 2). The book explains the concepts very clearly, information is presented in a way that is easy to understand and the content is engaging. I have read other books on machine learning and wish I'd started with this one.

The book is very good as far as theory is concerned. But when I ran the chapter 2 end to end example on Google colab, I got the following error: AttributeError: module 'urllib' has no attribute 'request'. Moreover, "urllib" has been superseded by "urllib3".

Very detailed hands-on machine learning book with Tensorflow2. Nice syllabus and a lot to practice.

i start learning machine learning with this book and cleared most of concepts regarding machine learning

Excellent book. Well written, interesting and clear.

Well structured booked, walks you through the fundamentals and hints you the next steps.

One of the most digestible books out there with great clarity and examples that help you grasp the concepts. For someone familiar with python and an idea of the modules used in DS and ML, this book would be the next step. Item arrived in excellent condition.

Wie schon der Vorgänger ist die neue Version mMn das beste Buch um schnell aber fundiert in die Welt des Machine Learning einzusteigen. Klar ist, dass es sich um ein anwendungsorientiertes Werk handelt, aber auch die Theorie und Mathematik kommt nicht zu kurz. Im Vergleich zum Vorgänger gibts etwa 250 Seiten mehr (550 alt vs. 800 neu), diese sind etwas dünner (womöglich Probleme mit Textmarkern) dafür aber in Farbe und das Buch als Ganzes fällt somit nicht wesentlich dicker aus. Besonders die neuen Kapitel über GANs sind für mich ein Highlight, natürlich aber auch die Verwendung von Keras und TensorFlow 2.0.

Já havia lido a primeira edição do material e fiquei bastante satisfeito com as modificações do segundo. O livro é impresso em cores e apresenta detalhes da implementação de várias técnicas e algoritmos de Machine Learning. Definitivamente é uma boa escolha para quem quer se aventurar na parte prática e sair da teoria. Os pacotes e a liguagem que são utilizados (Python, Scikit-Learn, Keras e TensorFlow) são bem adequados. A única ressalva que faço é também relacionada a sua maior qualidade: o fato do livro ser extremamente prático infelizmente peca na teoria. Dessa forma, recomendo que ele seja utilizado por pessoas que já tenham conhecimento da teoria de ML ou que ele seja utilizado junto a outro material que tenha a teoria mais forte.

Excelent book with lots of details and good explanation. Definitely one of the best books available.

Great coding examples & very well written explanations. Overall good mix of theory + practical aspects!

Best book to practice machine learning

This is a very comprehensive book available on ML. Highly recommended.

What great book for new learner or someone only want to plug and play

Excellent!

Happy with the book.

Nonostante le ottime recensioni e lo sfavillante curriculum dell'autore, che alla fine mi avevano convinto all'acquisto, non ho trovato ne' coinvolgente ne' particolarmente illuminante il libro. L'esposizione non e' strutturata per insegnare, direi piu' per esibire. Fastidioso (ma non inatteso, avendo letto recensioni e struttura) il fatto che una parte del libro abbia esempi scritti per un toolkit A e un'altra li abbia per il toolkit B. Anche questo da' l'impressione che si sia buttato nel mucchio un po' di tutto quel che si aveva pronto a portata di mano, piu' che impegnarsi da zero in un progetto editoriale omogeneo. Nonostante l'interesse per il tema e le aspettative che avevo per questo libro, sto trovando sempre piu' indesiderabile e noioso proseguire con la lettura. Non lo consiglierei, le stesse informazioni si trovano con relativa facilita' in rete, spesso in modo piu' fruibile e ovviamente a costo zero.

Brilliant book

As other people have already pointed out, the kindle math typesetting is really bad. For a book that has such a heavy emphasis on math, that's a bit of a dealbreaker for me so I returned it. Shame, because the book looked pretty good. I read a sample chapter in PDF and the math typesetting was perfect. Come on Amazon... either have a working format or just use PDFs like the rest of the world...

Great read.

I have the first edition, and was mostly happy with that book. But that book is explained in terms of scikit and tensorflow, using older notation, which I find difficult to keep track of. This new 2nd edition is updated for Tensorflow 2, and the many code examples are Keras based (Tensorflow's version) which I find much easier to understand. The code snippets are all clear and well explained, and there is an entire collection of book code on Github as well. The amount of re-usable code makes it worth getting the book -so I got the 2nd Edition too. Writing a book like this much be an absolutely massive amount of work - the volume of well-organized material (over 800 pages, some 250 pages more than the predecessor), the code, the excellent explanations .. even the use of color is helpful to understanding, not just a decoration. Complex concepts are explained in digestible pieces, and follow a logical progression. Some sections end in " ..but this has a shortcoming X, which can be fixed by Y .." which is then covered in detail in the next chapter. Where the material becomes too esoteric, pointers are given in the right directions to follow. Many reasearchers can shave months off their projects by studying the book - which can also be read as a reference work - just looking up the material of interest. I started in the middle, went straight into chapter 15 on RNNs, as I need that material now, and immediately felt at home with the discussion without having gone through chapters 0-14. (I'll read those later...) In addition to compiling executable notebooks with code on Github, the author has helpfully referenced many classical and more recent papers, and collected them on his site. This collection is of great interest in itself. And being so embedded in the ML world as the author is, he can talk with authority on what works and what doesn't. When he says something has been found to work well, on a certain class of problems, one is ready to believe it. I have been buying computer books for over 40 years, too many, and this book is in my top five, ever. Excellent, excellent book.

The book is great! However, my book has missing pages from 101-132 (it is printed the pages 229-260 instead). Should I return it and buy another one? Does anyone also have the same issue? Please let me know what should I do.

O livro é um excelente guia para quem deseja tanto aprender como implementar modelos de aprendizagem de máquina. Diversos exemplos são utilizados que tratam de problemas de regressão, classificação e de aprendizagem não supervisionada. Além disso, traz o Tensorflow 2.0 e o Keras para os problemas de Deep Learning. O livro foi impresso em cores o que é um diferencial em relação aos livros publicados pela O’Reilly.

Python Machine Learning by Packet - 3rd edition will be out Dec 1 2019. The Packet book gives more of a deeper understanding mathematically, No color in the print book but a PDF is in color (grab the PDF for $5-10 when on promo at Packet). While this print book by O'reilly is more visual and illustrative in color it lacks a deep understanding mathematically, it's more visual which is helpful to grasp the basics faster. Cons No PDF to follow when doing hands on learning, got to flip pages with the brick sized print book. I have both books from O'reilly and Packet( (2nd edition) for a complete picture of the subject. Not a Huge fan of slow and scriptic Python, so I apply myself with structured more robust Java using Spark, MLlib and DL4J with online tutorials. Too Bad there aren't any "good" Java based ML theory books out there. The Fashion is Python.

Wer das hier durchgearbeitet und verstanden hat, kann sich ohne Bedenken bei den KI-Abteilungen von Amazon oder Google bewerben. Davor steht aber ein gutes Stück Arbeit. Das Buch ist nichts für Leute, die nur einen Überblick wollen, was Machine Learning eigentlich genau ist. Es geht an vielen Stellen sehr tief ins Detail und behandelt trotzdem fast alle Bereiche von klassischem ML bis zu den trendigen Deep- und Reinforcement Learning. Das gelingt vor allem auch deshalb, weil zu dem Buch ein Github-Projekt gehört, in dem sich zu jedem Kapitel ein Jupyter-Notebook mit allen Python-Code-Beispielen, weiteren Erläuterungen sowie umfangreichen Lösungen zu den Praxisaufgaben befindet. Zum Teil tobt sich der Autor da richtig aus und programmiert mal eben einen rudimentären Synthesizer, nur um die RNN-generierten Sequenzen im Stil von Bach hörbar zu machen... Natürlich ist das zum Teil auch Spielerei und hat an manchen Stellen noch Hello-World / Proof-of-Concept Charakter - aber das macht das Thema ja so interessant - es geht, irgendwie, aber soll auch anregen, das auf eigene Anwendungsfälle zu übertragen. Genial ist auch, wie schnell der Autor die neue überarbeitete Auflage herausgebracht hat, um konsequent mit Tensorflow 2 und Keras zu arbeiten, was sich doch deutlich von der ersten Auflage unterscheidet.

I am a computer scientist but not an AI specialist. I read this book more or less page by page, omit the practical exercises, and learn incredibly much. What are the terms used in the discussion? What do they mean precisely (supervised learning vs. reinforcement learning etc.)? How do I select one over the other? How many hidden layers should a neurol network have? Very important to me: it is fun to read, too. This is not a popular book, it is a science book. For that audience, it is easy reading with high benefit.

In some moments the book is very didactic, in other moments it is very heavy, both in terms of statistical theory and mainly in terms of the algebra discipline. A big problem is that the book's Github is not complete: there are several practical exercises whose solution is not available.

Número de estrellas : 5 Añadir un Título: Excelente libro. Añadir una reseña: El libro abarca una amplia variedad de temas y tiene ejercicios donde te llevan de la mano para que practiques lo que vas aprendiendo. Mi principal interés en este libro es el uso de redes neuronales para el análisis de secuencias y el libro tiene un capítulo completo dedicado a esta área (aún no he llegado a este capítulo). Es muy importante recordar que el contenido del libro asume que se tienen conocimientos previos de programación en Python, álgebra y un poco de estadística por lo que es conveniente tener una pequeña base teórica antes para aprovechar el contenido al máximo.

it is one of the my 3 preferred books! Very aligned with the current state of the art. It describes from CV to standard ML. Good introduction to reinforcement learning and auto-encoder. Also it describes SGD in a very complete way.

Preso come complemento a libri più teorici che parlano dello stesso argomento. Il più grande vantaggio di questo libro è la possibilità di vedere con mano come molti algoritmi si traducono in codice. Copre la maggior parte degli argomenti di questa materia e inserisce riferimenti per ogni argomento nel caso si voglia approfondire una certa tematica. Inoltre (quasi) tutti gli esercizi sono forniti con soluzione che potete trovare sia sul libro che sul repository github dell'autore (che viene costantemente aggiornato).

This book was exactly what I was looking for. I have a stats background but it predates Machine Learning so I needed a fairly broad overview and a guide to the different packages that are out there. He covers a large number of topics with an emphasis on showing you the code to use which is really helpful. Also some math but its more to let you know a little bit about what's under the hood when using the packages. Plenty of diagrams and graphics are presented along with the explanations.

It really irks me that a book that costs $75 dollars has been printed on really cheap stock and you can see the individual dots on some pages because it was probably printed on-demand on a giant ink-jet printer. Can you please at least get color laser printers for this? It's annoying every time I open the book I feel like I could've just purchased a PDF/epub version and printed it on my own dang color laser. This book is great, and it deserves better printing Amazon!!!

Good either for someone who is starting in the field or for an expert who wants to get working and be productive.

Un buen libro, bien estructurado, combina la explicación de los temas tratados con ejemplos de código usando TensorFlow 2 y Keras, abarcando los aspectos principales para aprender Machine Learning (primera parte del libro) y Deep Learing (segunda parte), Hay muchos libros sobre ML+DL, algunos realmente buenos, para mi este es uno de los mejores.

Das Buch ist gut organisiert und hat viele Beispiele. Leider gibt es nicht detalierte oder Mathematische Erklärung. Das Buch ist gut geeignet, Wenn man nur die Konzepte lernen möchte.

This has to be one of the best hands-on machine learning books out there. If you have the 1st edition and thought it was good, I can highly recommend the 2nd. It is in full colour, has expanded content and most importantly has been updated for Tensorflow 2 and Keras (Tensorflow's preferred high level API). The only reason I didn't give it 5 stars and I have never given a book a 5 star review, is I thought it was lacking some practical detail around object detection and localisation, semantic segmentation and dealing with large datasets that don't fit into memory, those subjects are covered but not in a lot of detail and without code examples.

Testo di riferimento per il machine learning. Espone con chiarezza tutti e tre i metodi fondamentali di apprendimento supervisionato non supervisionato per rinforzo. Passa in rassegna tutti i principali classificatori, I metodi di regressione finì alle reti neurali sia con le librerie keras sia con tensorflow.

Es la segunda edicion de un libro que ya habia estudiado previamente y considero que la puesta al dia ha sido excelente

This book finally got me started on machine learning - something I have not managed with a lot of other resources. It covers a lot of ground, both in theory and the practical application. Recommended. Just make sure that you do not buy the Kindle version, as others pointed out (I bought the hardcover).

Ich habe mir das Buch im Rahmen der fünf Weiterbildungstage im Unternehmen besorgt und war (als Python Anfänger) erstaunt, welche Ergebnisse in kurzer Zeit erzielt werden können. Das Buch leitet durch die verschiedenen Schritte und ist gelungenermaßen "hands-on" konzipiert. Dabei wird auf die einzelnen Blöcke des Source Codes ausreichend eingeganen, sodass man alles gut nachvollziehen kann.

As the title says, the book is amazing to those who have some knowledge and wants to really learn the coding side and know how to use this wonderful python library. I actually read the old version and just started reading this new version.

This is a great book from a great author who took the time to go through the essential details that most books just rush through. Also liked the color images and code segments. Overall, a great second edition of a very popular book on this subject.

If you are a newcomer to ML, like myself, this is a very good place to start. Every concept and methodology is clearly introduced and illustrated with easy-to-follow examples. The "hands-on" on the title is really there for a reason. Definitely a very good buy. I strongly recommend it. Perhaps it would benefit from a list of acronyms (there are plenty of them in the book, and it is sometimes easy to forget what they mean, especially if you read it at spaced intervals), and a more thorough index, but these are only minor faults.