- List Price: $80.00
- Save: $50.57 (63%)
- FREE return shipping at the end of the semester.
- Access codes and supplements are not guaranteed with rentals.
Deep Learning (Adaptive Computation and Machine Learning series) Illustrated Edition
|New from||Used from|
Enter your mobile number or email address below and we'll send you a link to download the free Kindle App. Then you can start reading Kindle books on your smartphone, tablet, or computer - no Kindle device required.
To get the free app, enter your mobile phone number.
Frequently bought together
Customers who viewed this item also viewed
Deep learning has taken the world of technology by storm since the beginning of the decade. There was a need for a textbook for students, practitioners, and instructors that includes basic concepts, practical aspects, and advanced research topics. This is the first comprehensive textbook on the subject, written by some of the most innovative and prolific researchers in the field. This will be a reference for years to come.―Yann LeCun, Director of AI Research, Facebook; Silver Professor of Computer Science, Data Science, and Neuroscience, New York University
- Grade level : 12 and up
- Item Weight : 2.8 pounds
- Hardcover : 800 pages
- ISBN-10 : 0262035618
- ISBN-13 : 978-0262035613
- Dimensions : 9.1 x 7.2 x 1.1 inches
- Publisher : The MIT Press; Illustrated edition (November 18, 2016)
- Reading level : 18 and up
- Language: : English
- Best Sellers Rank: #15,302 in Books (See Top 100 in Books)
- Customer Reviews:
Top reviews from the United States
There was a problem filtering reviews right now. Please try again later.
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 audience--the 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/off-topic for a neural network book
(containing linear algebra, probability, and so on)
and Part III is written in a superficial way--so 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 half-decent 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 math-phobic 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 hand-wavy at places and
read like "you can do this to achieve that." It is impossible to fully reconstruct the methods from the
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 (sort-of 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
pre-requisites like basic linear algebra/probability basics. On the other hand, the PGM-heavy approach implicitly
increases the pre-requisites 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 PGM-centric 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.
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.
If it’s for the people who want to get started with deep learning, it’s completely off topic, since it presents the mathematical nitty-gritty of the deep learning algorithms without mentioning any specifics of how to train a convo-net 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.
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.
Top reviews from other countries
The worst of all is not that but the content. The figures are corrupted (I have included a couple of pictures but they are many more) in multiple places in such a way that it is difficult or impossible to decipher what could have been written.
Overall it looks like the book was rushed without proofreading or quality survey: it is the worst book I have bought in many years.
Of course, even though the book is long (700+ pages) it ends up feeling too short because each sub-field might only get 20-30 pages, but the book does give a good enough grounding to start a literature research, and highlighting hte key papers and insights. For myself, what has bee most valuable is seeing how it all fits together, which reading a random paper is hard to get.
Of course, there are lots of videos/courses/books out there, but this is the only one I've seen that is as comprehensive as this book. I've read it to cover-to-cover, and it is proving a great foundation to go and read more practical books and do projects using Tensorflow/Keras etc. Highly recommend.
The rewarding book is Chollet's. This one by Goodfellow is better suited to experts in the field, to have an excellent reference book in their hands.
"in practice this formula means that"
"This is widely used in the field, because.."
"this was fist proven as a success approach by.."
"this is our short review of the competition results.."
"the intuition behind this is.."
"this was never proven in practice.."
"from the common sense point of view.."
"technologically this is feasible since.."
"this approach allows to fit the batch into RAM memory.."
This books just "mechanically" throws the math expressions at unsuspecting user.
Never attempting to make a conceptual/functional/common sense introduction.
You will not find a single line of Python/R code in the book.
Not a single review of existing NN frameworks/libraries.
You will not find anything about technology and/or methodology of data collection, data cleaning, outliers detection, practical hints on training etc
Never trying to connect to any publications (i.e. other than the authors) in the field.
Never ever bringing the meaning of the formulas into discussion.
Deservedly, 3 out 5.