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

This book should be regarded as a "gold-standard" for technical books. It balances theory and practice, has exercises (actually with answers!) and covers a tremendous breadth and depth.The book starts out in a refreshingly unconventional way of giving you a crash course in ML concepts before diving in to an end-to-end project. I note that one reviewer didn't like that but I liked it a lot. While a lot of it will go over your head if you lack experience (and the author assumes you don't have much), it gives you appreciation of what an overall real-life project might look like. The rest of the book is spent unpacking each of those stages.The first part of the book looks at more "classical" or traditional machine learning concepts like linear regression, logistic regression, SVMs, decision trees, ensemble learning and unsupervised models. Along the way you learn a lot of data science best-practises and how to train and test things properly.The second part dives into deep learning, progressing from general neural networks to CNNs, RNNs, LSTMs, autoencoders and GANs. You get a flavour of how GPT models work. Other topics covered in this section are Tensorflow and Keras (including a part on deploying models) and a chapter on another paradigm: reinforcement learning.Geron doesn't shy away from the math but gives you enough theory to appreciate the detail if you like that, and explains it in intuitive ways and with code. Some of the formulas can look intimidating but they are unpacked and explained well.There are review questions and/or exercises at the end of each chapter. One of my biggest frustrations with technical books in general is when they give you questions but no answers. Here, you get answers and also worked code in the provided notebooks, which is amazing. Other technical authors: take note. The exercises are often quite challenging to implement or at least open-ended, but I believe that to be a good thing. I learnt a lot from doing them (I'll admit I didn't do all of them!).The writing is clear, engaging and often humourous.To sum up, if you want to learn more about ML, I highly recommend this book. This review is for the 2nd edition but I'll be buying the 3rd edition and will definitely be re-reading. There is so much great information to take in. Thanks to the author for this masterpiece.

I found the book 'Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow' to be an excellent resource for learning the fundamentals of machine learning. The author does a great job of breaking down complex concepts and explaining them in an easy-to-understand way, making it accessible even for beginners.The practical examples and exercises throughout the book were incredibly helpful in solidifying my understanding of the material. I appreciated that the book not only covered the theory behind machine learning but also provided hands-on experience using popular tools like Scikit-Learn, Keras, and TensorFlow.Overall, I highly recommend this book for anyone interested in learning about machine learning and building intelligent systems.

Have been advised by many people this is possibly the best book on ML but held off on owning a hard copy as I found it a bit expensive so I grabbed this one roughly 50% off. The level of detail is amazing and everything ML related is nicely explained. It's nice to see the book was printed in colour which makes the code easier to follow and reproduce. I also liked the layout very much and found it helped to make the book flow - will happily read this cover to cover. The quality of the paper is on thin side but to be fair the content is worth more - I own other similar size ML books printed in black and white that cost more with half the content because it was printed on thick paper. Highly recommended for anyone with an interest in ML.

Clearly explained, well organised, detailed, very good code exercises.

Great introduction to different models and more importantly data preprocessing.

Loved this book, I recommend whenever I'm asked by people who want to get practical with ML. The chapters follow a logical order and are well worth working though carefully, following all the code with the result being that you'll get a very solid foundation for ML, covering both the data science driven statistical methods (first half of the book) and xNN/RL (2nd half). It fills the gap between books that are too hello world/simplistic and the other end which is greek alphabet soup. Loved the fact you can just spin up a colab notebook and point it at the github for the book and just get on with playing with all the examples...no messing around with lots of local machine setup. Oh and if you need a refresher on python or linear algebra, then he has that covered too, just look at the github only chapters. If I could give 6 stars, I would...just buy it!Am now waiting for the 3rd edition, avail in US but not in UK yet...

Great book, just what I was looking for. It's at exactly the right level for me. The author writes in a very straightforward, easy to understand way, but without oversimplifying. If you already know your way around python/pandas and jupyter notebooks, and have a decent grasp of linear algebra & stats (nothing beyond A-level standard), this is the book for you. I'm currently about half way through it, just getting into the neural networks stuff. Have started dabbling with kaggle as well. It's fascinating, and a lot of the concepts are actually pretty straightforward.

This is an excellent book for machine learning, data science and deep learning. The print quality is great, the author's style of explaining concepts and going into enough depth of the subject is also amazing. I use this as my reference for any machine learning project. It is not just for beginners, it also teaches a lot of advanced concept including creating your custom models, optimisers and loss functions in Tensorflow. It goes from really basic machine learning modelling like linear or logistic regression to advance Deep Learning all the way to generative modelling. It assumes basic prior knowledge in python.