Deep Learning (Adaptive Computation and Machine Learning) Hardcover – November 18, 2016

Very clear, very comprehensive

Comment

N N Taleb

February 1, 2018

Format: HardcoverVerified Purchase

Very clear exposition, does the math without getting lost in the details. Although many of the concepts of the introductory first 100 pages can be found elsewhere, they are presented with remarkable cut-to-the-chase clarity.

21 people found this helpful

A constant theme here is that 'this works better than that' for practical reasons not for underlying theoretical ...

Comment

S. Matthews

November 18, 2016

Format: Hardcover

This is, to invoke a technical reviewer cliché, a 'valuable' book. Read it and you will have a detailed and sophisticated practical understanding of the state of the art in neural networks technology. Interestingly, I also suspect it will remain current for a long time, because reading it I came to more and more of an impression that neural network technology (at least in the current iteration) is plateauing.

Why? Because this book also makes very clear - is completely honest - that neural networks are a 'folk' technology (though they do not use those words): Neural networks work (in fact they work unbelievably well - at least, as Geoffrey Hinton himself has remarked, given unbelievably powerful computers), but the underlying theory is very limited and there is no reason to think that it will become less limited, and the lack of a theory means that there is no convincing 'gradient', to use an appropriate metaphor, for future development. A constant theme here is that 'this works better than that' for practical reasons not for underlying theoretical reasons. Neural networks are engineering, they are not applied mathematics, and this is very much, and very effectively, an engineer's book.

272 people found this helpful

The classic textbook on Deep Learning

Comment

Stergios Papadimitriou

August 25, 2018

Format: HardcoverVerified Purchase

Deep Learning is the promising direction towards general purpose effective artificial intelligence.
There is an explosion of fruitful research in recent years and a lot of applications pursued mainly from technology giants as Google, Amazon, etc. and outstanding research institutions.
The book "Deep Learning " by Ian Goodfellow, Yoshua Bengio, Aaron Gourville, is an excellent piece of work.
They manage to present rather difficult things in an understandable manner. The theoretical presentation is outstanding typical of "classic" books. Also, the book stays close to the practical applicability of all the methods and discusses applications extensively.
There are a lot of other useful books on deep learning that follow a more practical approach by focusing on a particular deep learning software package, but this one book is certainly much more essential since it provides the required theoretical background in order to be able to do serious work on deep learning.
I consider the book as "must have" for anyone that works on deep learning either in an academic or in an industrial environment.

Wonderful survey text on deep learning

Comment

Hoss

December 31, 2017

Format: HardcoverVerified Purchase

Wonderful survey text on deep learning. Anyone reading this should already have a background in machine learning. The text does a very good job of informing the reader what has been done and was is being done for neural networks. In addition it provides experienced gained by various researchers over the past 10 years.

I took away one star as I think there should be some additional explanation of the math. Currently, the reader must seek referenced papers for additional understanding.

One person found this helpful

Comment

August 20, 2018

Format: HardcoverVerified Purchase

I find this book pretty frustrating because it skims over things at a really high level. I didn't need to buy this book to read hand-wavey explanations of neural networks. Before this, I read a very applied book (recommended) "Hands on Machine learning with Scikit learn and tensorflow" which also describes NNs at a high level, but implementation at the same time. I was hoping to get a bit deeper understanding than that, but I don't think that this book added much on top of what I got from that one. Even things I already had learned about, such as factor analysis (ch 13) were described at such a high level that to get the idea I had to go back to my previous notes (from Bishop "Pattern recognition and machine learning", also recommended). As a reader, I like to be taken through the development of an idea, but this book just throws out names of methods as if a list of bullet points were converted to paragraph form.

The book is printed as awfully as a pirated book. In addition, the cover color is totally different with the photo they provided....

Comment

Customer images

See all customer images

Most recent customer reviews

jingnan xue

Severe print problem!!!!

Published 3 days ago

Nzeyi

Great book to have but there are disconnections between theory and practice

After reading the first 8 chapters of the book, I decided to make this review highlighting a couple of points:
- there are better resources out there on the preparatory...Read more

Published 6 days ago

Uttaran Bhattacharya

Best book on the subject, delivered copy not the best

The cover is not flat. It has a bend going outwards from the spine. Excellent otherwise.

Published 8 days ago

Vamseedhar

Water damaged book

There was visible water damage to book. But the outer package was good and dry.

Published 8 days ago

MegatronTop Contributor: Guitars

Theoretical bible for deep learning

Pure theory. Very comprehensive. The introduction alone is an incredible recap of the history of machine learning/artificial intelligence.Read more

Published 15 days ago

Reza

very fragmented text

Although authors are pioneers in the field and did great work, the book is very poorly written. Too much abstract information, lots of unnecessary details and lots of missing...Read more

Great book with all Linear Algebra refresh in it.

Amazon Customer

Five Stars

Of limited use, but good to own

anil nerode

No student will be able to learn much from the definition-free problem-free exposition of underlying linear algebra and statistics. Those who know both areas can learn a lot.Read more

If you are interest in deep learning, probably you need it.

Gianantonio Bissaro

This book is far from perfect and the chapter on linear algebra seems to me pretty superfluous. In any case this is the more complete text on the subject available on the...Read more

This is almost a brand-new book! Very good quality!

coalbowl

Very good quality!