Advanced Machine Learning with Python: Solve data science problems by mastering cutting-edge machine learning techniques in Python

It is very good book and cover the information that we looking for

Worth it

Great product!

I bought this book, because I liked the idea of explaining concepts as they are implemented in python. Unfortunately, the quality of this book is very poor. It is entirely printed in b/w. That makes figures unreadable. Example: A color coded heat map just printed in b/w. In particular if you also add number into the mix, so that everything is just a dark grey blob. Or a plot of clustered data point in which the different classes can be distinguished only by a tiny change in their grey shading, maybe. The text itself looks just cheaply printed. Again, printed in b/w, which makes the python-listings hard to read and understand. This makes understanding whats going on harder than it need to be. For the price of around 37€, the code could have been printed in a better readable quality with some form of syntax highlighting. The code itself contains some errors. That is strange, since it should have been executed by the author,no?

A few word about myself: I am a Analyst, I have a MSc. in Mathematics and Statistics and do analytics for a living. While I have studied about neural networks and machine learning a while ago, only past year have I (re)-discovered the power of neural nets and Deep Learning. In my quest to improve my knowledge, I have taken many certificates in ML and have bought a few books about Machine Learning. Among these are: -Python Machine Learning by Sebastian Raschka (recommended) -Building Machine Learning Systems with Python by by Luis Pedro Coelho and Willi Richert (nice to have for additional perspective) However, I wanted to go beyond what one can find in those two books. The topics I was specifically interested in were: -Deep Belief Networks (inc. Restricted Boltzmann Machine) -Autoencoders -Convolutional Neural Networks So where does Advanced Machine Learning rank among these? I must say, and that will be my main criticism of the book that it is not for the faint of heart. It is fast, sometimes too fast... I suppose there is so much you can put in 250 pages to explain about these topics, and it is easy to become lost. However, do not get me wrong. This book is a small gem in itself. Why? Because while I have found online many tutorials or courses about the topics I was interested, the book gives you additional information and explanations that I haven't found anywhere else. How do you set your hyper-parameters in a CNN? What is the depth exactly representing, what are the current architectures, are they really all that good? Why? It is the difference between the how and the more precise what and why. Tutorials online are great but many people just do things without clearly showing why. This books gives you the clues. In conclusion, for me currently (after having bought 8 books): The book is difficult but not super difficult. It gives more understanding and depth than I could ever obtain with all the material available online currently (including the very good Stanford courses). So, yes, I feel I am making progress. -Python Machine Learning by Sebastian Raschka is the way to go for Machine Learning foundations -Advanced Machine Learning with Python by John Hearty is a super helpful complement to what one can already find online dispersed all over the place, it just make sense with better hindsight.