Hands–On Machine Learning with Scikit–Learn and TensorFlow

Having just finished chapter 2, I'm finding this book goes into a lot of detail. Online courses I've taken go through a couple of steps to prepare the data, but this book really takes you through in much more depth. It shows you how to write custom transformers your data and how to make a pipeline and shows you how to evaluate your model as well. I'm really enjoying the book and I think anyone else who knows how to program already and wants to pick up machine learning should definitely pick up this book.

This book is a fantastic introduction to TensorFlow and pretty modern neural network techniques. I was a little worried buying this book that it would focus too much on Scikit Learn, but this is not the case. This book is approximately 50:50 Scikit and TensorFlow. I bought this book as I was using TensorFlow and neural networks for my Masters Thesis and it delivered exactly what I needed to kick start my research. A pretty concise summary of some methods and what to use to get started. It is an easy read and can be consumed pretty fast if you are even vaguely familiar with the underlying theory I wish I had more hands so I could give this book three thumbs up.

5* for the first half of the book, scikit learn. 3* for the second half, Tensor Flow. Nice examples with Jupyter notebooks. Good mix of practical with theoretical. The scikit learn section is a great reference, nice detailed explanation with good references for further reading to deepen your knowledge. The tensor flow part is weaker as examples become more complex. Chollet’s book Deep Learning with Python, which uses Keras is much stronger, as the examples are easier to understand as Keras is a simple layer over tensor flow to ease the use. Also Chollet explains the concepts better and nicely annotates his code. Buy this book for scikit learn and overall best practise for machine learning and data science. Buy Chollet’s Deep Learning using Python for practical deep learning itself. Overall still a practical book with Jupyter Notebook supplementary material.

Overall, it's an excellent book for both theoritical and practical. The theoratical part is easy to understand and the author let's you understand the material smoothly. Usually, books like this make you sleep, but this book stands out. Good job for the author.

Pretty good explanation of several aspects of Machine Learning. The author goes into a good deal of the mathematical background despite it being a practical book. e.g. I finally learned the step between quadratic programming (from convex optimisation) and SVMs. That said this is not an introductory book. You are expected to know Python and a good deal of the data libraries beforehand.

Covers everything from simple linear models, SVM, random forests right through to modern neural nets/deep learning: CNNs, RNN and reinforcement learning. The writing is excellent. It seemed like every time I wondered something the answer was in the next paragraph. The pace was perfect for me though I have done some of this before - I wonder if it moves too fast for some.

I have been studying AI on and off for over 25 years, and have worked on statistical modelling for the past 20 years, including at Caltech and in Wall Street. I am currently running a summer program on Machine Learning in finance at UCL and am writing positions papers on ML, AI and big data. I own a library of Mathematical Statistics, Modelling, AI, Pattern Recognition, Machine Learning, Python, R, etc books and I have to say that this book makes all the others redundant. This is like Wilmott/Hull is for finance, or Kernigen & Ritchie for C. This is so obviously written by a practitioner - someone who has done it and has the scars to show it. Even the title tells you this is for the grown-ups - forget R and all that crap, all roads lead to SKLearn and TensorFlow, via anaconda a Jupyter. Buy this book and "Elements of Statistical Learning" and you have all the library you ever need. If you don't want to get bogged down in the maths, then just buy this one.

This is a really excellent book for somene looking into starting seriously with Tensorflow. It provides all these small bits and pieces missing from the (sparse) official documentation and it can save you from hours of search through stackoverflow and github repos. As an added benefit you are taught in a structured way how to start with things. A great introduction for most people, more experienced users should probably have a look first. Highly recommended!

Ich war bis vor Kurzem der Meinung, dass sich ein Real-Programmer nicht mit so etwas wie Python die Hände schmutzig machen sollte. In Vorbereitung für ein Projekt habe ich es mir doch näher angeschaut. Über die Sprache kann man diskutieren, aber die Bibliotheken sind wirklich brauchbar und offensichtlich auch sehr effizient implementiert (es werden good old Fortran und C Bibliotheken aufgerufen). Das Buch bietet eine ausgezeichnete Einführung in die beiden wichtigsten Statistik-Bibliotheken scikit-learn und Tensorflow. Besonders beeindruckt hat mich Kapitel 2. Es wird ein Beispiel - die Prognose von Immobilienpreisen in Kalifornien - von A-Z genau präsentiert. Man lernt auch die mundanen aber in der Praxis sehr kritischen Dinge des Statistiker-Lebens. Wie schaut man sich die Daten möglichst anschaulich an, wie reinigt man sie, beseitigt missing-values ... So etwas habe ich in diesem Detail noch nie in einem Statistik-Lehrbuch gefunden. Es werden neben dem praktischen Kode im gesamten Buch aber auch die wichtigsten statistischen Eigenschaften besprochen, der Autor diskutiert das Verhalten von unterschiedlichen Optimierungsstrategien von Tensorflow ... Es bleiben natürlich immer auch Wünsche übrig. Ich hätte mir noch etwas mehr zum Thema Time-Series und Neural Networks gewünscht. Auch auf das keras package hätte der Autor etwas detaillierter eingehen können. Das ist offensichtlich geplant. Es gibt bereits die Ankündigung einer neuen Auflage für Juni 2019. Der Titel ist um "keras" erweitert. Eine gute Ergänzung zu diesem Buch ist Jake VanderPlas: Python Data Science Handbook. Mit diesen beiden Büchern erhält man eine solide Grundlage für das Gebiet. Man muss dann "nur noch" selber was machen und im echten Projektleben Erfahrung sammeln.

This is a great book if you want to try Deep Learning by yourself. But one warning, don't buy Kindle edition. The mathematical equations are a mess unless you have a big tablets.

By far the most complete and accurate hands-on book on machine learning and deep learning. Author has done a remarkable job in giving details in just the right amount. No over-doing or under-doing in this one. Code given in the jupyter notebooks works like a charm and covers almost everything. Highly Recommended!!

Must read

Great. Absolutely the practical walkaround of the ML landscape you would expect from the title. It does require textbook support for readers seeking complete understanding of the maths behind the different approaches.