3.5/5. It's an up-to-date and gentle survey covering a wide range of deep learning topics. Each topic has a mix of math and implementation. I found the math sections to be more useful: there is a good balance of rigor vs. intuition. I did not find the implementations useful as they relied on a custom library. Since the book is open source, a reader can easily contribute a fix by opening a PR.
While many other books fail in combining theory and practical implementation, this book thrives at exactly that. The D2L package might take some getting used to, but once you have seen an example or two the remaining code snippets are generally intuitive and truly help in understanding the accompanying theory. Great read!
A gentle introduction for beginners but lacks the rigor of Mathematics and deep understanding. Still, it's a good start: enough to know the field but requires more effort and other materials to understand and use the concepts effectively.
This book is very simple for beginner who put first step in deep learning field. It explain clearly basis thing from simple model such as linear regression, logistic regression to complex model as NN, CNN or even Transformer.