I bought the first version of this book . and now also the second. The new version is very comprehensive. If you are using Python - its almost a reference. I also like the emphasis on Neural networks (and tensorflow) - which (in my view) is where the Python community is heading. I am also planning to use this book in my teaching @Oxford Uni. The data pre-processing are also good. I found the sequence flow slightly unusual - but for an expert level audience .. its not a major issue

Easy to read, well structured and very useful. The only caveat I would add is that this is for Python programmers who have a reasonable background in maths but are new to ML, not those in ML looking to pick up Python.

I am impressed about how this book was designed, its layout is very logic and can take you from the basic terms to complicated knowledge, action is louder than speaking, it also use Scikit-learn to teach newbies like me to practice those theories, I will recommend it.

P.S. The book focus on supervised and unsupervised machine learning methods, but not much about reinforcement learning.

I am using theis book to teach data science

Great book! Presenting the machine learning algorithms and some of the elements of the linked theory, altogether with Python code is really useful.

I purchased two Packt publications on AI and ML. Both are extremely poorly written, poorly researched and extremely difficult to follow. Language, terms, descriptions and content are difficult to follow at best, or archaic at worst. Nothing is explained and require additional research at almost every step. Screenshots sizes are inconsistent, do not add value and in many cases are blown up to an extent where screenshot fonts well exceeds the book print. This gives the impression images are added to maximize uptake of the book print real estate. In some cases, you have to work out that some instructions are included in screenshots, rather than within the actual text. I have come to the conclusion that Packt publications are no more than résumé fillers for their authors. The publication includes no references. I learned more from YouTube videos. Beware of catchy one liners such as 'A Comprehensive Guide to Building Intelligent Apps for Python Beginners and Developers'. This is nothing more than bait. The book is an insult to the word 'comprehensive', and the best use python beginners may make of this publication is to send it back immediately for a refund and look for an academic and referenced text - Item not as described.

I’m using this book alongside the machine learning nanodegree by Udacity and it’s brilliant in explaining the why behind key concepts of machine learning!

Basic multivariate statistics methods wrapped up in fancy machine learning terminology, which all comes down to methods that were around for decades to say the least. This is one of the books for the SQL data base administrators turned "data scientists" who don't understand statistics or data but want to get some results that probably don't mean anything sensible. Badly written, filled with useless code (why printing code on paper???) with virtually no mathematical notation or explanation of statistical methodology used by various methods implemented in sevaral Python packages. If you need to learn hot to run linear or logistic regression without understanding what you are doing this is a book to buy, though I have seen better written ones.

It is a great book. Read it and enjoy the ideas.

Le livre trouve un bon équilibre entre l'application du machine learning en python et les raisonnements mathématiques derrière les algorithmes. Il est très complet et je le conseille pour ceux qui souhaitent explorer le sujet en profondeur. Le code est mis a disposition pour téléchargement ce qui permet de tester directement ce qui est expliqué.

This book is excellent for the following demographic:

People who already have a decent level of skill and experience in statistics who want to:

- 1) Elevate their understanding of ML techniques without absolutely breaking their skull on dense theory

- 2) Learn how to implement the algorithms in Python and gain moderate proficiency in sci-kit learn

I would say it's not a beginner's book, but more for intermediates. I am half-way through and find it a little challenging, but definitely attainable. This balance I consider to be putting me right in the sweet spot for learning. To judge whether you're a good candidate for this book, you can compare your experience and skill to me :

I started this book after earning a PhD in the social sciences, which basically gave me good coverage in inferential and applied statistics (T, F distributions, p-values, confidence intervals, linear regression, one-way and factorial ANOVA, PCA, etc.). I also took a machine learning graduate course at my university and a few online courses in introductory ML for R. All of this background gave me solid grounding in statistics. With all this I still find this book somewhat challenging, but definitely not too hard. I'd say without my background I would find this book hard to get through. There is linear algebra, concepts like minimizing cost functions, bias/variance tradeoff, learning from errors, etc. So, if you are just starting out or reading the previous sentence and don't know what I'm talking about, I would recommend learning more stats fundamentals before starting this.

After you gain some proficiency in stats, come learn this book and elevate your understanding of the algorithms, add nuance to them, integrate them into your mental conceptual structures more fully (e.g. you'll know more nuances of ML, e.g. which subsets of algorithms are preferred for controlling more of the bias, variance, how random forest is basically bagging with a twist, how adaboost's treatment of classification errors has kind of an element of perceptron implementation, and many more).

This is one of the best beginner's books out there. If anyone wants to start ML they have to go through this book, although the DL part of the book uses TF version 1 which is not used anymore. You will also learn a lot of numpy, pandas and matplotlib features

内容が近く、おすすめです。早く購入すればよかった。