Machine Learning with PyTorch and Scikit-Learn: Develop machine learning and deep learning models with Python

This is a great book on machine learning. Topics covered are extensive - from beginner level to advanced topics including math behind different algorithms. However, not "all" algorithms are covered. Please go through the table of contents.The first part - 11 chapters - covers machine learning concepts and second part covers advanced topics with Pytorch. There are lots of excellent code and they work!!The quality of the book I received is excellent. I have gone through all 742 pages, and it has held up very well!!I used Jupyter notebook to run all examples. I created a new notebook and copied and pasted the code and ran them. This approach worked very well for me. At the same time, I could experiment with my take on the code snippets and definitely added to my knowledge.Only issue I have is on the second part of the book discussing PyTorch: (1) Some packages are a bit older version: e.g., transformer 4.9.1 whereas current version is 4.48+. It took some tweaking/recoding to get the examples working. (2) There is not much discussion on why certain architecture was chosen - e.g., number of layers, is there a rule of thumb on how to improve performance by changing these parameters? Even with CUDA the code run for a long time. Therefore, experimenting with different values of parameters become too time consuming. (3) On the same note, if I can achieve test accuracy of 90%+ using logistic regression and almost the same (perhaps one or two percent better with PyTorch with IMDB movie review dataset and that two much faster why should I use PyTorch for this dataset? Obviously, PyTorch is for certain types of problems. Discussions can be included by not adding to the exhaustive (and apt) contents.Personally I was disappointed by lack of any example on time series.Must have for ML practitioner as a reference and guide.

Very comprehensive and well written book. The authors show how every layer underneath is created in every chapter. Thanks to the authors, I was finally able to wrap my head around back-propagation

The book covers a wide range of useful terms in the never-ending machine learning landscape. The pages are on black and white style and the relevance of explained concepts are far from perfect.

I started with Seb's book on Build a Large Language Model and was impressed by the quality of the contents that I went back to this book to get the basics. Excellent material backed up by the github sample content. I am only in the early stages of reading this book but am hooked onto it and will continue to work through.

Machine Learning can often be intimidating whether you are starting out or already a practitioner. It is easy to get stuck on one concept, walk away frustrated, or just copy that code you find on StackOverflow without really understanding what it does. What the authors of this book, Machine Learning with PyTorch and Scikit-Learn, have managed to do is to keep the reader engaged giving a deeper illustration as to how the concepts work. In this book, you get practical code examples, a detailed explanation of how the various library tools work, and exposure to the mathematical concepts behind machine learning algorithms. In addition, what I like about the book unlike many machine learning books is that the authors have managed to intuitively explain how each algorithm works, how to use them, and the mistake you need to avoid.I have not read a Machine Learning book that better explains Transformers as this one does. The authors have managed to give a detailed dive into this model architecture through well-explained codes and illustrations. As a reader, you walk away having intuitively grasped the concepts of attention and self-attention in ways that will make this crucial NLP architecture clear. You get exposed to pre-trained models from HuggingFace library which really helps to have that hands-on experience working with large datasets.As they have done throughout the book, the authors have broken down those complex mathematical operations into simple explanations that are easy to follow. What I generally like about the book is how it seamlessly connects all the chapters, not throwing off the reader. There are numerous external resources quoted throughout the book. This helps spark that curiosity to dig deeper. In addition, you get introduced to PyTorch, getting exposed to all those sophisticated libraries that help the reader learn how to maximize their compute power. I would say it is not intimidating at all even if you have not used PyTorch before.I would recommend this book to anybody seeking a textbook that is both easy to read and modern in its content. If were to rate the book I will give it a 10/10 as it really applies to both beginners and experienced practitioners, covers all the concepts one needs to apply in their operations, and acts as a quick reference.