I am surprised by how poorly written this book is. I eagerly bought it based on all the positive reviews it had received.
Bad mistake. Only a few of the reviews clearly state the obvious problems of this book. Oddly enough, these informative
reviews tend to attract aggressively negative comments of an almost personal nature.
The disconnect between the majority of cloyingly effusive reviews of this book and the reality of how it is written
is quite flabbergasting. I do not wish to speculate on the reason for this but it does sometimes does occur with
a first book in an important area or when dealing with pioneer authors with a cult following.
First of all, it is not clear who is the audiencethe writing does not provide details at the level one
expects from a textbook. It also does not provide a good overview ("big picture thinking"). Advanced readers
would also not gain much because it is too superficial, when it comes to the advanced topics (final 35% of book).
More than half of this book reads like a bibliographic notes section of a book, and the authors seem
to be have no understanding of the didactic intention of a textbook (beyond a collation or importance sampling
of various topics). In other words, these portions read
like a prose description of a bibliography, with equations thrown in for annotation. The level of
detail is more similar to an expanded ACM Computing Surveys article rather than a textbook in
several chapters. At the other extreme of audience expectation, we have a review of linear algebra in the beginning,
which is a waste of useful space that could have been spent on actual explanations in other
chapters. If you don't know linear algebra already, you cannot really hope to follow
anything (especially in the way the book is written). In any case, the linear
algebra introduced in that chapter is too poorly written to even brush up on known material so who is that for?
As a practical matter, Part I of the book is mostly redundant/offtopic for a neural network book
(containing linear algebra, probability, and so on)
and Part III is written in a superficial wayso only a third of the book is remotely useful.
Other than a chapter on optimization algorithms (good description of algorithms like
Adam), I do not see even a single chapter that has done a halfdecent job of presenting
algorithms with the proper conceptual framework. The presentation style is unnecessarily terse,
and dry, and is stylistically more similar to a research paper rather than a book.
It is understood that any machine learning book would have some mathematical sophistication, but the
main problem is caused by a lack of concern on part of the authors in promoting readability and an inability to
put themselves in reader shoes (surprisingly enough, some defensive responses to negative reviews tend to place
blame on mathphobic readers). At the end of the day, it is the author's responsibility to make
notational and organizational choices that are likely to maximize understanding.
Good mathematicians have excellent manners while choosing notation (you don't use nested
subscripts/superscripts/functions if you possess the clarity to do it more simply).
And no, math equations are not the same as algorithms only a small part of it. Where is the rest?
Where is the algorithm described? Where is the conceptual framework?
Where is the intuition? Where are the pseudocodes? Where are the illustrations? Where are the examples?
No, I am not asking for recipes or Python code. Just some decent writing, details, and explanations.
The sections on applications, LSTM and convolutional neural networks are handwavy at places and
read like "you can do this to achieve that." It is impossible to fully reconstruct the methods from the
description provided.
A large part of the book (including restricted Boltzmann machines)
is so tightly integrated with Probabilistic Graphical models (PGM), so that it loses its neural network focus.
This portion is also in the latter part of the book that is written in a rather superficial way and
therefore it implicitly creates another prerequisite of being very used to PGM (sortof knowing it wouldn't be enough). .
Keep in mind that the PGM view of neural networks is not the dominant view today, from either a practitioner
or a research point of view. So why the focus on PGM, if they don't have the space to elaborate?
On the one hand, the authors make a futile attempt at promoting accessibility by discussing redundant
prerequisites like basic linear algebra/probability basics. On the other hand, the PGMheavy approach implicitly
increases the prerequisites to include an even more advanced machine learning topic than neural networks
(with a 1200+ page book of its own). What the authors are doing is the equivalent of trying to teach someone
how to multiply two numbers as a special case of tensor multiplication. Even for RNNs with deterministic hidden states
they feel the need to couch it as a graphical model. It is useful to connect areas, but mixing them
is a bad idea. Look at Hinton's course. It does explain the connection between Boltzmann machines and PGM
very nicely, but one can easily follow RBM without having to bear the constant burden of a PGMcentric view.
One fact that I think played a role in these types of strategic errors of judgement is the fact that the
lead author is a fresh PhD graduate There is no substitute for experience when it comes to maturity
in writing ability (irrespective of how good a researcher someone is). Mature writers have the ability to put
themselves in reader shoes and have a good sense of what is conceptually important. The
authors clearly miss the forest from the trees, with chapter titles like "Confronting
the partition function." The book is an example of the fact that a first book in an important area with the name of
a pioneer author in it is not necessarily a qualification for being considered a good book.
I am not hesitant to call it out. The emperor has no clothes.
Other Sellers on Amazon
S$63.00
+ S$1.99 delivery
+ S$1.99 delivery
Sold by:
Charlie_B
S$97.64
+ FREE Delivery
+ FREE Delivery
Sold by:
The Book Depository Limited
Sold by:
Amazon SG
Have one to sell?
Deep Learning Hardcover – Illustrated, 18 April 2017
See all formats and editions
Hide other formats and editions
Amazon Price

New from  Used from 
Hardcover, Illustrated
""

S$65.00

S$63.00  — 
Enhance your purchase
Frequently bought together
Customers who viewed this item also viewed
Page 1 of 1 Start overPage 1 of 1
 Mathematics for Machine LearningMarc Peter DeisenrothPaperbackIn stock.
 Deep Learning Illustrated: A Visual, Interactive Guide to Artificial IntelligenceJon KrohnPaperback
 Artificial Intelligence: A Modern Approach, Global EditionStuart RussellPaperbackOnly 2 left in stock.
 Neural Networks and Deep Learning: A TextbookCharu C. AggarwalHardcoverOnly 1 left in stock.
 The Algorithm Design ManualSteve S. SkienaHardcover
 Deep Learning for Coders with fastai and PyTorch: AI Applications Without a PhDSylvain GuggerPaperbackUsually dispatched within 4 to 5 days.
Product details
 Language : English
 Hardcover : 800 pages
 ISBN10 : 0262035618
 ISBN13 : 9780262035613
 Reading age : 18 years and up

Best Sellers Rank:
1,355 in Books (See Top 100 in Books)
 16 in Computer Science
 20 in Graphics & Multimedia Software
 43 in School Education & Teaching
 Customer reviews:
Product description
Review
[T]he AI bible... the text should be mandatory reading by all data scientists and machine learning practitioners to get a proper foothold in this rapidly growing area of nextgen technology.
―Daniel D. Gutierrez, insideBIGDATAAbout the Author
Ian Goodfellow is a Research Scientist at Google.
Yoshua Bengio is Professor of Computer Science at the Université de Montré al.
Aaron Courville is Assistant Professor of Computer Science at the Université de Montréal.
Customers who bought this item also bought
Page 1 of 1 Start overPage 1 of 1
No customer reviews
5 star (0%) 

0% 
4 star (0%) 

0% 
3 star (0%) 

0% 
2 star (0%) 

0% 
1 star (0%) 

0% 
How are ratings calculated?
To calculate the overall star rating and percentage breakdown by star, we do not use a simple average. Instead, our system considers things like how recent a review is and if the reviewer bought the item on Amazon. It also analyses reviews to verify trustworthiness.
Most helpful customer reviews on Amazon.com
Amazon.com:
3.7 out of 5 stars
263 reviews
slag
2.0 out of 5 stars
A surprisingly poor bookwho is the audience?
27 September 2017 
Published on Amazon.comVerified Purchase
2.0 out of 5 stars
A surprisingly poor bookwho is the audience?
Reviewed in the United States on 27 September 2017
I am surprised by how poorly written this book is. I eagerly bought it based on all the positive reviews it had received.Reviewed in the United States on 27 September 2017
Bad mistake. Only a few of the reviews clearly state the obvious problems of this book. Oddly enough, these informative
reviews tend to attract aggressively negative comments of an almost personal nature.
The disconnect between the majority of cloyingly effusive reviews of this book and the reality of how it is written
is quite flabbergasting. I do not wish to speculate on the reason for this but it does sometimes does occur with
a first book in an important area or when dealing with pioneer authors with a cult following.
First of all, it is not clear who is the audiencethe writing does not provide details at the level one
expects from a textbook. It also does not provide a good overview ("big picture thinking"). Advanced readers
would also not gain much because it is too superficial, when it comes to the advanced topics (final 35% of book).
More than half of this book reads like a bibliographic notes section of a book, and the authors seem
to be have no understanding of the didactic intention of a textbook (beyond a collation or importance sampling
of various topics). In other words, these portions read
like a prose description of a bibliography, with equations thrown in for annotation. The level of
detail is more similar to an expanded ACM Computing Surveys article rather than a textbook in
several chapters. At the other extreme of audience expectation, we have a review of linear algebra in the beginning,
which is a waste of useful space that could have been spent on actual explanations in other
chapters. If you don't know linear algebra already, you cannot really hope to follow
anything (especially in the way the book is written). In any case, the linear
algebra introduced in that chapter is too poorly written to even brush up on known material so who is that for?
As a practical matter, Part I of the book is mostly redundant/offtopic for a neural network book
(containing linear algebra, probability, and so on)
and Part III is written in a superficial wayso only a third of the book is remotely useful.
Other than a chapter on optimization algorithms (good description of algorithms like
Adam), I do not see even a single chapter that has done a halfdecent job of presenting
algorithms with the proper conceptual framework. The presentation style is unnecessarily terse,
and dry, and is stylistically more similar to a research paper rather than a book.
It is understood that any machine learning book would have some mathematical sophistication, but the
main problem is caused by a lack of concern on part of the authors in promoting readability and an inability to
put themselves in reader shoes (surprisingly enough, some defensive responses to negative reviews tend to place
blame on mathphobic readers). At the end of the day, it is the author's responsibility to make
notational and organizational choices that are likely to maximize understanding.
Good mathematicians have excellent manners while choosing notation (you don't use nested
subscripts/superscripts/functions if you possess the clarity to do it more simply).
And no, math equations are not the same as algorithms only a small part of it. Where is the rest?
Where is the algorithm described? Where is the conceptual framework?
Where is the intuition? Where are the pseudocodes? Where are the illustrations? Where are the examples?
No, I am not asking for recipes or Python code. Just some decent writing, details, and explanations.
The sections on applications, LSTM and convolutional neural networks are handwavy at places and
read like "you can do this to achieve that." It is impossible to fully reconstruct the methods from the
description provided.
A large part of the book (including restricted Boltzmann machines)
is so tightly integrated with Probabilistic Graphical models (PGM), so that it loses its neural network focus.
This portion is also in the latter part of the book that is written in a rather superficial way and
therefore it implicitly creates another prerequisite of being very used to PGM (sortof knowing it wouldn't be enough). .
Keep in mind that the PGM view of neural networks is not the dominant view today, from either a practitioner
or a research point of view. So why the focus on PGM, if they don't have the space to elaborate?
On the one hand, the authors make a futile attempt at promoting accessibility by discussing redundant
prerequisites like basic linear algebra/probability basics. On the other hand, the PGMheavy approach implicitly
increases the prerequisites to include an even more advanced machine learning topic than neural networks
(with a 1200+ page book of its own). What the authors are doing is the equivalent of trying to teach someone
how to multiply two numbers as a special case of tensor multiplication. Even for RNNs with deterministic hidden states
they feel the need to couch it as a graphical model. It is useful to connect areas, but mixing them
is a bad idea. Look at Hinton's course. It does explain the connection between Boltzmann machines and PGM
very nicely, but one can easily follow RBM without having to bear the constant burden of a PGMcentric view.
One fact that I think played a role in these types of strategic errors of judgement is the fact that the
lead author is a fresh PhD graduate There is no substitute for experience when it comes to maturity
in writing ability (irrespective of how good a researcher someone is). Mature writers have the ability to put
themselves in reader shoes and have a good sense of what is conceptually important. The
authors clearly miss the forest from the trees, with chapter titles like "Confronting
the partition function." The book is an example of the fact that a first book in an important area with the name of
a pioneer author in it is not necessarily a qualification for being considered a good book.
I am not hesitant to call it out. The emperor has no clothes.
Images in this review
862 people found this helpful
dolphone
2.0 out of 5 stars
Not very good :(
10 November 2017 
Published on Amazon.comVerified Purchase
Have I been reading amazon book reviews backwards and you are supposed to count the white stars?
This book is not going to teach you machine learning and I don't even know why they bothered including the math sections because they just restate definitions, of varying relevance, that you may or may not know, in a confusing way.
It isn't going to teach you the math or even serve as a refresher on the math. At best, if you already know the math you can decode what they are saying and nod along.
It feels like the book is compressed. They write out overly elaborate mathematical symbols and then you just have to think it through and remember that Andrew NG video where he actually explained the concept.
So in short the math is overly elaborate and it really doesn't explain anything. The math review section is worthless. They don't have examples or practice problems. They expect you to do all the work, which you should, with another book.
This book is not going to teach you machine learning and I don't even know why they bothered including the math sections because they just restate definitions, of varying relevance, that you may or may not know, in a confusing way.
It isn't going to teach you the math or even serve as a refresher on the math. At best, if you already know the math you can decode what they are saying and nod along.
It feels like the book is compressed. They write out overly elaborate mathematical symbols and then you just have to think it through and remember that Andrew NG video where he actually explained the concept.
So in short the math is overly elaborate and it really doesn't explain anything. The math review section is worthless. They don't have examples or practice problems. They expect you to do all the work, which you should, with another book.
95 people found this helpful
mackster
1.0 out of 5 stars
A rushed, poorly written guide of how the "experts" can't really explain what Deep Learning is
16 May 2018 
Published on Amazon.comVerified Purchase
This book, in every sense of the word, is rushed. I think the authors wanted to establish themselves as leaders of this youngish field, but does so by sacrificing quality. It also shows that Deep Learning theory has been there for a long time, known by another name called Neural Networks. The interesting algorithms are of MLP, Back Propagation and the classical neural networks. The optimization methods such as Adam are the ones that are new and interesting, and the only ones worthy of in this book. So, essentially, what you get from this book is use A for X, B for Y and C for Z type of dry, unintuitive, badly written waste of paper.
As for the structure of the book, it's like an example of how not to structure a book. It has some linear algebra, probability at the start (not good enough, and confuses more people and wastes paper). Goes on to prove other algorithms such as PCA (yeah, ok!). Then, talks about how this architecture works for this and that architecture.
So, yeah, if you really want to try out deep learning, don't buy this book. Set up Tensorflow/pytorch/ other library, run the tutorials, find an architecture for the problem you are interested in and start tweaking that. You will have far more fun and would have saved your money.
The praise that this book gets is beyond me. Did Musk even read this book? I doubt it.
As for the structure of the book, it's like an example of how not to structure a book. It has some linear algebra, probability at the start (not good enough, and confuses more people and wastes paper). Goes on to prove other algorithms such as PCA (yeah, ok!). Then, talks about how this architecture works for this and that architecture.
So, yeah, if you really want to try out deep learning, don't buy this book. Set up Tensorflow/pytorch/ other library, run the tutorials, find an architecture for the problem you are interested in and start tweaking that. You will have far more fun and would have saved your money.
The praise that this book gets is beyond me. Did Musk even read this book? I doubt it.
87 people found this helpful
aflyax
2.0 out of 5 stars
Unclear who the intended audience is — deep learning practitioners aren’t it, though...
8 July 2017 
Published on Amazon.comVerified Purchase
The book was frankly a disappointment. It was unclear who the intended audience was. If it were the people who wanted to find out academic background behind Deep Learning, then this would be too superficial for them. In some cases, it’s not even clear who and how someone would benefit from the presented material. (For instance, whom was the Linear Algebra chapter written for? It’s woefully impossible to understand if you don’t already know linear algebra. And if you already know it, it’s unnecessary. And if you sort of know it and wanted to brush up, what linear algebra they present in the chapter is not enough to go through the math in the book. So…)
If it’s for the people who want to get started with deep learning, it’s completely off topic, since it presents the mathematical nittygritty of the deep learning algorithms without mentioning any specifics of how to train a convonet for example. The amount of information on convolutional networks and LSTMs is worse than on any number of blogs on deep learning or Wikipedia.
If you’re really interested in Math behind Deep Learning out of curiousity (perhaps you’re a mathematician who wants to know what this deep learning thing is all about) perhaps this is a book for you. Otherwise, do yourself a favor and watch/read Andrej Karpathy’s Stanford class.
If it’s for the people who want to get started with deep learning, it’s completely off topic, since it presents the mathematical nittygritty of the deep learning algorithms without mentioning any specifics of how to train a convonet for example. The amount of information on convolutional networks and LSTMs is worse than on any number of blogs on deep learning or Wikipedia.
If you’re really interested in Math behind Deep Learning out of curiousity (perhaps you’re a mathematician who wants to know what this deep learning thing is all about) perhaps this is a book for you. Otherwise, do yourself a favor and watch/read Andrej Karpathy’s Stanford class.
217 people found this helpful
Amazon Customer
1.0 out of 5 stars
It does not worth the money for the quality of the print.
23 June 2018 
Published on Amazon.comVerified Purchase
I suspect it is pirated, I can’t imagine how it is original copy, leave the detached cover aside binding is poor and print quality of most pages are distorted. I know the content of the book(I’ve read it) and I can’t believe it is being sold like this.
1.0 out of 5 stars
It does not worth the money for the quality of the print.
Reviewed in the United States on 23 June 2018
I suspect it is pirated, I can’t imagine how it is original copy, leave the detached cover aside binding is poor and print quality of most pages are distorted. I know the content of the book(I’ve read it) and I can’t believe it is being sold like this.
Reviewed in the United States on 23 June 2018
Images in this review
31 people found this helpful