Deep Learning: Foundations and Concepts

This author is very good at explaining the methods and theory. Very illuminating and insightful. Very well organized materials.

I like the book, especially the chapter which introduces attention mechanism and transformer.

Deep Learning: Foundations and Concepts by Christopher M. Bishop and Hugh Bishop is a comprehensive and accessible introduction to the world of deep learning. The book effectively balances theoretical depth with practical insights, making it suitable for both beginners and experienced practitioners.Key strengths of the book include:Clear and concise explanations: The authors do an excellent job of breaking down complex concepts into easily understandable terms, making the material accessible to a wide range of readers.Strong mathematical foundation: The book provides a solid mathematical foundation for understanding deep learning algorithms, but it avoids excessive mathematical formalism, making it engaging for readers with varying levels of mathematical background.Practical applications: The book covers a wide range of real-world applications, such as computer vision, natural language processing, and speech recognition, providing practical examples to illustrate the concepts.Up-to-date coverage: The book covers the latest advancements in deep learning, including attention mechanisms, transformer models, and generative adversarial networks.Potential areas for improvement:More hands-on exercises: While the book provides theoretical explanations, it could benefit from more practical exercises and coding examples to reinforce learning.Deeper dives into specific topics: For readers who want to delve deeper into specific topics, such as reinforcement learning or unsupervised learning, additional resources or references could be helpful.Overall, Deep Learning: Foundations and Concepts is an excellent resource for anyone interested in learning about deep learning. It provides a clear and comprehensive introduction to the field, making it a valuable addition to any machine learning enthusiast's library.

This is quite mathematically rigorous so make sure you're comfortable with your vector calculus and derivations. Otherwise, this is a phenomenal book as it combines it with the mathematical rigor with amazing diagrams, plots and images that demonstrate the intuition behind these common deep learning topics (which is quite rare). For example, he showed a derivation of RMSProp and it's close intuition from physics principles.If you're into research or theory and want to contribute to the field, this is a wonderful entry. If you're in industry and just implementing models that are based on pre-existing theory, you may want to try a more hands-on book.

I'm feeling lucky.This is incredibly, unspeakably, impossibly good book.I've seen the book at the CVPR conference, and hesitated a bit before buying it. $90 after all.But I can't be happier with my purchase. It's simply the best book on Deep Learning - and on Machine Learning - I've seen in 20 years. It gives a very accessible and intuitive introduction in many topics - and, at the same time, preserves the mathematical rigor. For example, the chapter on transformers is the very, very best description of a topic I've seen so far.The book also contains all the info on the ML basics - from multivariate distributions to EM algorithm. Again, it is written very candidly - and, at the same time, preserves theoretical foundations. It is probably slightly less "mathy" than the "Pattern Recognition and Machine Learning" book by Bishop - which is a previous iteration of this text. But much, much more accessible as well. It explains "narrow" topics in plain English. You may read it in this textbook, and then go back to "Pattern Recognition" if you want to get a slightly deeper math for the same topic.Also the book is very recent and covers the hottest and most recent topics, like Diffusion Models.Saved me lots, lots of time and effort - instead of digging through a heap of research papers I can nos just read a chapter from this book.Many thanks to Chris Bishop for writing it!

Excellent book with a great mathematical explanation of how deep learning works. For me, the mathematical perspective is probably the best of the DL books I've read, and it provides a good intuition. There are other books with good code samples, but, without the intuition I've seen a lot of folks waste precious time... Definitely would recommend.

I bought this books to acquaint myself on deep learning, but the 2 chapters "Convolutional networks" and "Transformers" are written badly and did not get anything out of this other than a general architecture. How the information is passed and used from one layer to the other is completely missed. Besides those 2 chapters on deep learning, the rest of the book is on topics related to machine learning is easy to follow (if you have some decent background on matrix analysis and statistics).

I was very happy until began to see some wrong mathematical steps justifications, and errors.Is like enter in math details doing errors, then lose its worth to had this math details, better to go on the surface. For instance Eq 2.90appears a ln D (natural logarithm of D)Which is omitted in a simplification process , saying the reason is D don't depends on p(x).The error actually is:where is ln D, actually goes a sum of probabilities multiplied by D*lnDand the reason for disappear (not for omit), is cause limit when D -->0 D * ln D = 0---------------My disappointment isn't the found errors itself, but I haven't confidence in go on more sophisticated topics, cause there could appear similar issues, but undetectable by me.