Penguin Random House Deep Learning (Adaptive Computation and Machine Learning series)

helpful for anymore who wants an introductory (and broad) background to the field

This is a good comprehensive textbook starting at the basics (math, statistics and fundaments) of Machine Learning and Deep Learning. It is well aligned with eg MOOC courses in Machine Learning should you want to deepen your understanding. However, there are of course newer books, but this is worth buying a reference and as said a comprehensive textbook.

This book serves as an excellent reference book but also as a book to settle down and contextualise your knowledge. For example, I went to read up on contrastive divergence which is often bunched together with restricted boltzmann machines (naturally). The text on contrastive divergence was within a practically self-contained chapter on monte carlo sampling. It was beautiful. The authors also succeed in contextualising these topics against all the necessary central theory but also the state of the art. This book deserves a place in anyone's collection even if you feel you possess other works which may contain the same topics.

This is a great theoretical book on deep learning, covering many topics. The writing is clear, the maths not too difficult if you concentrate, and is fairly self contained. There are lectures about the chapters of the book on you tube. Really useful if you combine it with another source, such as Rajesh Sharma's 2020 SIGGRAPH ML and Neural Networks course, available on you tube, which covers much of the same deep learning material but with python/tensorflow/keras code.

It is a great book for those that want some theoritical understanding of methods that underpin deep learning technologies. It is not for those who just want to learn how to apply deep learning technologies without needing the maths and theories. It requires some understanding of linear algebra, advanced probability theories, vector calculus and optimisation to make the understanding of the book natural. The authors did well to present a refresher on these topics but I don't still think anyone who has got no primer courses on these topics before will be able to cope very well.

Great book. It's one of the main DL reference works, comprehensive, and expertly written. RE: other reviewers that experienced printing issues. My copy is in perfect condition. No missing pages, no repeats, no corrupted images. Looks great.

This is genuinely good reading. As any thorough monograph it hold the essential foundations needed to get to understand all the fun stuff. And the fun stuff there is then plenty of to dive into. Find this a must read to get going w deep learning if you want to get serious about it.

I bought it to look up certain things, but the page numbers in the register are all wrong by 5-10 pages. That is very annoying! So far I also haven't found good explanations or answers to any of my questions. I was expecting more given that this is a classic!

Spiegazioni efficaci, notato che, per argomenti a me gia' ben noti, ci sono sottigliezze che danno spunti importanti. Quindi ritengo, estrapolando, che anche per le cose nuove che ho letto non sia una semplice riscrittura di concetti, ma hanno dato valore aggiunto. L'argomento e' in continua evoluzione, il libro non e' recentissimo, ma capire tali basi permette di affrontare i nuovi algoritmi. E' un libro da studiare, non un manuale d'uso e manutenzione.

Libro excepcional sobre deep learning, considerado una de las principales referencias en la materia. Es increíblemente completo y profundo, cubre desde los fundamentos hasta conceptos avanzados, con un enfoque muy académico. Sin embargo, no es un libro sencillo: requiere una base sólida en matemáticas y machine learning para poder aprovecharlo bien. Quizás resulte más útil para investigadores, doctorandos o quienes quieran profundizar a nivel teórico que para principiantes. Aun así, es una obra imprescindible en cualquier biblioteca de inteligencia artificial.

Great book for aspiring deep learning enthusiasts

This book is possibly currently unique in its coverage of the latest ideas in the field of deep learning -- and it is a very convenient and good survey of fundamental concepts (linear algebra, optimization, performance metrics, activation function types), different network types (multi-layer perceptron, convolutional neural networks, and recurrent neural networks), practical considerations (data set, training and validation, implementation), and applications (comments on existing real-world/commercial uses). The final 235 pages of the content portion of the book is dedicated to topics in "Deep Learning Research", and these topics are truly at the current frontier. Another reviewer said that one could gain the same knowledge of cutting-edge research by reading all of the latest papers (from academia and industry), but the "research" section of this book offers the following: Selection of the most notable research by the very experienced authors of the book, and collection of similar research in to a broader discussion of themes, and the additional insights. The book covers very advanced and new ideas currently being explored, and it is very nice to be able to have a consistent and coherent presentation of all of those ideas. However, the book is also packed with valuable observations and pointers about more basic aspects of deep learning implementations and practices -- and such commentary is in depth and includes substantial analysis and mathematical derivation (in an intuitive presentation that often includes graphs illustrating the phenomenon). As someone with an intermediate level of knowledge and experience of neural networks, I am really grateful for this book, because seems like the ideal resource for learning cutting-edge ideas and practices, with context. The book has excellent scope and depth, and I am confident that anyone with a solid background in linear algebra, calculus, statistics, and general machine learning, and basic neural networks (multi-layer perceptrons) will find this book to be very exciting and perhaps unique in its ability to take the reader to the next level and a new frontier. I was personally excited to learn about the idea of representing the dependencies of intermediate quantities by directed graphs, and how this can be used to perform calculations for recurrent neural networks efficiently. And I think the long chapter on recurrent neural networks is very helpful. Having said all of this, I think only people with significant working knowledge and experience with neural networks and mathematics -- people whose academic or professional focus has been neural networks for at least a year or two -- would benefit from this book. This book answers a lot of the deeper questions that one is likely to have while developing a solid understanding of the fundamentals, and that's one of the book's tremendous values, but this book assumes an understanding of the fundamentals (but does briskly cover the basics). I think this book is a perfect follow-up book for the excellent book "Neural Network Design (2nd edition)" by Hagan, Demuth, Beale, and de Jesus, and I highly recommend the latter for gaining the solid background needed to have a thrilling experience with the "Deep Learning" book. In summary, I am very glad this "Deep Learning" book was written, and I think the "Deep Learning" book will be a great benefit to a lot of people, and to the evolution of the field.

Item arrived damage, with badly printed pages. I tried to contact the seller, but messages cannot be delivered to it.