What do you think?
Rate this book
Deep Learning with R
Summary
Deep Learning with R introduces the world of deep learning using the powerful Keras library and its R language interface. The book builds your understanding of deep learning through intuitive explanations and practical examples.
Purchase of the print book includes a free eBook in PDF, Kindle, and ePub formats from Manning Publications.
About the Technology
Machine learning has made remarkable progress in recent years. Deep-learning systems now enable previously impossible smart applications, revolutionizing image recognition and natural-language processing, and identifying complex patterns in data. The Keras deep-learning library provides data scientists and developers working in R a state-of-the-art toolset for tackling deep-learning tasks.
About the Book
Deep Learning with R introduces the world of deep learning using the powerful Keras library and its R language interface. Initially written for Python as Deep Learning with Python by Keras creator and Google AI researcher François Chollet and adapted for R by RStudio founder J. J. Allaire, this book builds your understanding of deep learning through intuitive explanations and practical examples. You'll practice your new skills with R-based applications in computer vision, natural-language processing, and generative models.
What's Inside
Deep learning from first principles
Setting up your own deep-learning environment
Image classification and generation
Deep learning for text and sequences
About the Reader
You'll need intermediate R programming skills. No previous experience with machine learning or deep learning is assumed.
About the Authors
François Chollet is a deep-learning researcher at Google and the author of the Keras library.
J.J. Allaire is the founder of RStudio and the author of the R interfaces to TensorFlow and Keras.
Deep Learning with R introduces the world of deep learning using the powerful Keras library and its R language interface. The book builds your understanding of deep learning through intuitive explanations and practical examples.
Purchase of the print book includes a free eBook in PDF, Kindle, and ePub formats from Manning Publications.
About the Technology
Machine learning has made remarkable progress in recent years. Deep-learning systems now enable previously impossible smart applications, revolutionizing image recognition and natural-language processing, and identifying complex patterns in data. The Keras deep-learning library provides data scientists and developers working in R a state-of-the-art toolset for tackling deep-learning tasks.
About the Book
Deep Learning with R introduces the world of deep learning using the powerful Keras library and its R language interface. Initially written for Python as Deep Learning with Python by Keras creator and Google AI researcher François Chollet and adapted for R by RStudio founder J. J. Allaire, this book builds your understanding of deep learning through intuitive explanations and practical examples. You'll practice your new skills with R-based applications in computer vision, natural-language processing, and generative models.
What's Inside
Deep learning from first principles
Setting up your own deep-learning environment
Image classification and generation
Deep learning for text and sequences
About the Reader
You'll need intermediate R programming skills. No previous experience with machine learning or deep learning is assumed.
About the Authors
François Chollet is a deep-learning researcher at Google and the author of the Keras library.
J.J. Allaire is the founder of RStudio and the author of the R interfaces to TensorFlow and Keras.
335 pages, Paperback
First published January 1, 2018
23 people are currently reading
221 people want to read
About the author
François Chollet
20 books123 followersFrançois Chollet is a French engineer and researcher in artificial intelligence.
Ratings & Reviews
Friends & Following
Create a free account to discover what your friends think of this book!
Community Reviews
Displaying 1 - 12 of 12 reviews
January 2, 2019
Of the many books, articles, and videos I have watched and read on the topic of deep learning, this book stands head and shoulders above the rest. Incredibly clear and straightforward explication. I can't recommend it highly enough.
June 7, 2018
This book fills a nice niche in that it is the only reliable reference for using the R interface to Keras. Of course, one of the authors is the founder of RStudio and main author of the Keras library. The first three (and most important) chapters are free. But come on... just make your online documentation really good and save a book for the deep dive. I'll largely be reviewing the free chapters.
The best part about this book is hands-down the examples. The examples in chapter 3 cover the most common cases: a binary classifier, a multiclass classifier and a regression problem. These were easy enough to figure out and generalize to my problem. Also of great use was the section on validation and overfitting. The code samples were clear and well thought-out, and the writing was entertaining (for a textbook).
There was lots of stuff that I didn't like though. This is a book from a programmers point of view. The explanation of tensor calculus using nested for-loops left my eyes watering. I would have liked to see a reference to an undergraduate explanation of tensor calculus (which I had to seek out myself). The organization of the first fout chapters was not smooth. I found myself constantly flipping between two, three and four because a lot of the information is repeated, but not consistently. For example, I was looking for an explanation of the activation functions and there are different tables and explanations in both chapters two and three. I think this book is due for some serious editing.
This book has a lot of potential to be a good, authoritative source on using the Keras library. But I often found myself jumping between random Coursera videos, textbook chapters and chapters within this book to get a good sense for what model I should be implementing.
The best part about this book is hands-down the examples. The examples in chapter 3 cover the most common cases: a binary classifier, a multiclass classifier and a regression problem. These were easy enough to figure out and generalize to my problem. Also of great use was the section on validation and overfitting. The code samples were clear and well thought-out, and the writing was entertaining (for a textbook).
There was lots of stuff that I didn't like though. This is a book from a programmers point of view. The explanation of tensor calculus using nested for-loops left my eyes watering. I would have liked to see a reference to an undergraduate explanation of tensor calculus (which I had to seek out myself). The organization of the first fout chapters was not smooth. I found myself constantly flipping between two, three and four because a lot of the information is repeated, but not consistently. For example, I was looking for an explanation of the activation functions and there are different tables and explanations in both chapters two and three. I think this book is due for some serious editing.
This book has a lot of potential to be a good, authoritative source on using the Keras library. But I often found myself jumping between random Coursera videos, textbook chapters and chapters within this book to get a good sense for what model I should be implementing.
August 11, 2018
Good book, but unless you have a substantial investment in R infrastructure that you can't afford to abandon, you should get the Python version of it instead. The deep neural network community has clearly standardized on Python, not R, and it is simply the better choice for any new project in that area if you get to pick.
Also, do not believe the author's facile claims that this is the only book you need. This book explains almost nothing about how deep learning actually works, and is actually more like a user manual for Keras. Provided you actually want an instruction manual for Keras, it's an excellent book. If you want to understand something about Deep Learning, go read the book by Goodfellow et al. They make a nice set, in either order or alternating between the two.
Also, do not believe the author's facile claims that this is the only book you need. This book explains almost nothing about how deep learning actually works, and is actually more like a user manual for Keras. Provided you actually want an instruction manual for Keras, it's an excellent book. If you want to understand something about Deep Learning, go read the book by Goodfellow et al. They make a nice set, in either order or alternating between the two.
April 3, 2018
Pretty nice book by the creator of Keras. Also my first approach to Deep Learning. A must read book for anyone trying to learn Keras on R. But...and this might be because my inexperience in Deep Learning...but...I feel like most of the examples showed just how to display accuracy percentages...but not actual predictions...and that happened as I wanted to reuse a convolutional network trained with my own to make image classification...all worked fine in theory...but could never used to make a prediction...and I think an example like this should had been included in the book...anyway..besides that...it's an awesome book...
October 5, 2019
While the difficulty of this books grows rapidly from chapter to chapter, Chollet somehow managed to keep things as simple and understandable as possible. A lot of this is due to his (brilliant) decision to eschew mathematical notation on favor of R code. Perhaps this is a detriment to the mathematically-minded, but as someone who learned stats through code, it made the topic so much more accessible.
October 6, 2019
An excellent introduction to Deep Learning. The author does a particularly good job putting Deep Learning into context (both social context and statistical context), which is sometimes missing from computer science oriented books. If you want to learn about Deep Learning and R is your language of choice this is the book for you. (There's also a version using Python if that's your preference).
March 30, 2018
The book is very good for R users to learn the state-of-the-art deep learning technology. This book provides many practical suggestions and intuitive explanations. It would be even better if these book can provide some exercises.
January 30, 2019
I am quite lost reading this book trying to understand how deep learning works.. I guess the R sample code would be useful, but I learned so much better by taking the coursera class and especially did the homework in terms of understanding the algorithms.
October 19, 2019
Even if not learning R the general chapters on deep learning are very good. The R code seemed sub-optimal as in more like Python code literally ported across to R, not as R-native as I think it should be for an R focused book.
September 28, 2020
It’s a great book for first contar with DL. However, I think their approach of “no math, just code” is the weakest point of the book imo. I get hey we’re going for a more approachable vibe, but I don’t think no maths at all is the way to go.
November 6, 2018
Loved it, and I will definitively go back to it many many times in my Deep Learning journey with R programming. The metaphor of the crumpled paper ball was perfect.
September 12, 2018
A clear introduction to an incredibly complex topic. A must read for all data scientists who use R and want to stay on the cutting edge.
Displaying 1 - 12 of 12 reviews