Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems

I have just finished Hands-On ML book and I cannot recommend it enough. I have been working as a Mobile Software Developer for 12 years and now I am thinking about trying something new. I remember some Math and Statistics from school but definitely not enough to get deep into the subject. From my experience, you can read the book and finish all the exercises without understanding any of the Math (although as author points out, it is beneficial if you understand the Math behind it - e.g. to understand why it works, read and implement papers). Book goes into the detail and explains the history of how we got there so it was fairly easy for me to follow and understand majority of the book. I missed this kind of detail from ML courses that I tried. You will also see significant papers explained - something that would be difficult for me to do alone at this point. However, one thing I appreciated the most were the exercises. In ML courses I tried, the exercises were simple and too easy to give you anything. Here it was a real challenge and I have a good feeling about what I learned by doing those exercises. There are also a lot of references for books or papers in case you want to focus on a specific area. One blind spot I am seeing though is focus on Keras/TensorFlow and GCP pipeline whereas the most examples on internet seem to be from PyTorch and AWS as a most popular cloud solution. However, as author points out, if you know one it will be easy for you to switch (I also reimplemented some of the PyTorch projects as part of exercises without too much difficulty). Still, I need to think about it and get some more PyTorch and AWS experience.

I bought three AI books this year and I ended up reading this one so far by Aurelien instead of the other (which was unfortunately in black & white, had misaligned paper cut, etc.). The book by Aurelien Geron (3rd edition) has better explanation, better visual aids, nicer print, etc. One thing I probably would suggest though, is to maybe do a similar code comments style/explanation like what was done in the third book that I got (Deep Learning With Python by Francis Chollet), which I just got but haven't read yet. Some of the code explanation is on the same page/area/line. Convenient. No flipping of pages...

Insightful and easy to follow.

Excellent book for beginners! Easy to follow with complete practice data and code

The content in this book is fantastic. I like the writing style, making it more enjoyable to read. The color visuals and codes are helpful and practical. Definitely something I will want to use as reference when studying and working. The book is thick, about 2inches (I thought it would be half of that), so making it a bit inconvenience to carry around to school or library. But I think it can't be thinner without no reducing the content inside. The paper quality could be better. It bleeds easily when using highlighters. The paper is quite thin that I could see text of the next page through the page I'm on. The glue type used to bind the book could be thicker, so it can hold these over 800 pages long book together longer. The glue is thinner compared to another book I have with similar number of pages, size and thickness. Overall, great content but need more quality check in terms of the physical appearance of the book.

Es una Calidad de libro. Espero una edición en PDF para comprarla con descuento porque ya tengo la de pasta. No es para compartirla, soy escritor y defiendo los derechos de los escritores a que se valore nuestro trabajo, es solo porque los apartamentos de hoy en día son muy pequeños y no hay mucho espacio para libros.

It's a very good introductory book to supervised and unsupervised learning algorithms. It has a lot of code and brief explanations of the theory. It's a very good start if you want to venture into the world of machine learning.

Excellent technical book