Bought it used and loved it. Excellent conditions and shipped really fast!!

The content of the book is too heavy. Lots of mathematical proofs where it appears the target audience is definitely people already in the field.The book misses the point about being a 'foundation' of Machine Learning.Yes, you should pass.

I have the first edition and decided to buy the second one too, because this book worth the money. If you are not sure about the purchase you can find full official PDF on the author's site and check if the book fits your expectationsYou need this book if: you are interesting in statistical machine learning and you have proper mathematical background.You do not need this book: if you are looking for a book with hands on content on deep learning and you are not interesting in the theoretical background why it actually works.A bit longer text. In the book you will find a systematic and rigorous treatment of statistical machine learning foundations (there is NO deep learning content in the book, because it's more an art than a science). Every chapter has excersizes, so the book will do for self study, although there is no publically available solution manual, at least as for now. It's important to highlight that the book is not a hands on manual, there is no codes of perceptron or regressions on keras, only pseudo code and formulas. To fully appreciate the content one needs to have a solid background in probability and linear algebra, if "law of iterated expectations" and "full column rank matrix" says you nothing, you would not enjoy the content.

This is defineltey an awesome book. If you have statistical background this book is definitely written for you. If you like applied machine learning this is not exactly your book. I use this book to teach statistical machine learning as an advanced course in statistics.

I’m using this book as a supplement for my second ML course as part of a MSCS program. Overall, I like its math orientation. It’s good for someone going through a course that first introduces the material in other ways (instructor intro to the material). Also, it is useful for someone who may have experience with ML packages and is now seeking the corresponding mathematical foundation.If you’re new to ML, then a potential shortcoming is that the reader is left to infer from the math what things mean. So, for someone with no ML background, this could be challenging. In that case, I would recommend pairing this book with something else - to get the key ideas - and then use this book for the mathematical foundation.This isn’t a programming book, but a true computer science book. There are some other good books available if your goal is to learn a specific library or tool from a programming perspective.I read a comment about the kindle version. I am using the iOS Kindle app. In portrait mode, the equations scale to the width of the device. When rotated to landscape, it scales approximately. So, I’ve had no trouble with readability or viewing the equations iOS. I can’t speak to the native Kindle or Android Kindle experience.The reason for the 4/5 rating is because I would have liked to have seen coverage of neural networks. That was intentionally omitted and they give a reason for this decision. While I don’t think they need to try to address Deep Learning, I feel that a foundational understanding of ML should include ANNs.I am glad to have this book as a reference in my collection.