Hands–On Machine Learning with Scikit–Learn and TensorFlow

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 theoryI wish I had more hands so I could give this book three thumbs up.

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.

I have started reading, just finished a few chapters. As of now I really like the chapter formats, introductory chapter, covering entire ML start to end.The 2nd part of the book is where in all the fun kicks in, but that would be bit difficult if you havent read the first part of the book.The foundations explained in the 1st half of the book are really usful for understanding the 2nd half of the book.That being even though I like tensor flow, it can be a bit difficult thinking about creating the graph and then executing it separately, it isnt that intuitive (well at least for me), I have also started to look into Keras which seems to be much easier to just get going, I was debating between TFLear and Keras as a highlevel API over TensorFlow but I seemed to like Keras - I guess it has a larger community.

Amazing book. I would just like to point out that the description for the kindle edition carries the disclaimer (in bold) that "Graphics in this book are printed in black and white". This is not true, they are very much in colour and this makes a huge positive difference, especially for graphical information presented in multiple dimensions.As an enthusiastic hobbyist, some of the descriptions of what is "under the hood" were slightly beyond my ability to fully comprehend. However, the book is so well-written that this becomes inspiring rather than frustrating. So my next project is to improve my math.

This book is extremely well written, concise, and very practical. One of the best books on the subject, doesn't require the reader to be a full-time mathematician fluent in Greek. I cannot recommend it enough.After I read a few chapters from a pdf version, I bought the paper version of the book because I liked it so much. Unfortunately, the print version is black and white and that makes some charts much less discernible, so I still use the pdf version to see the charts in color.

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.

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.

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.

N/A

Excelente libro, para quienes están empezando y para quienes tienen cierta experiencia en este campo.- Utiliza herramientas actuales y las librerías mas usadas.- Aplicaciones reales con datos reales.- Referencias a sitios web relacionados con el tema.- Ejercicios muy interesantes y actuales.- Conceptos muy bien explicados.En lo personal poseo cierta experiencia en estos temas y no esperaba mucho de este libro, pero al tenerlo y empezar a leerlo me fascino, un libro mus imágenes.y bien hecho y se nota desde las primeras paginas que el autor es un experto en el tema, las herramientas y los ejemplos son muy y repito muy prácticos, fácilmente puedes replicar el código de ejemplo para tus necesidades y tus propias aplicaciones de ML.Un Excelente libro, me atrevería a decir que de los mejores en la actualidad.Altamente Recomendable.

Para mi el mejor libro de Machine Learning, mu completo y con muy bueno ejemplos que van más haya de los típicos en otros libros.

Excellent text. Covers both the theory and the practice of modern machine learning, providing the reader with a solid background , needed to tackle the matter with confidence.

Machine learning books have become a dime a dozen. From the moment of receiving this one it was obvious this one stands out from the crowd. Having many such volumes what makes this book special is the depth of coverage in succinct english with examples that clearly illustrates the subject area being discussed.As a newbie to TensorFlow this book is a very good starting point in the journey to proficiency. If you are looking for concise starting points in the areas of machine learning concepts discussed, this book again hits the mark in a clarity not seen in the many other books now collecting dust in my library. The Greeks and mathematical proofs have thankfully left out as if you at the level the book is written to you don't really care anymore. Life's classroom frankly are your results, not a peer review and this book is very much for the practitioner not the academic looking to impress his colleagues in academia.This is a book worthy of being added to your machine learning library and in close proximity to the keyboard as you code to refresh what you thought you knew but long ago forgot was important. Just might donate my machine learning books to others at the local library as this book stands alone in taking up valuable space in a ever decreasing bookcase.