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.

  • Apple
  • Android
  • Windows Phone
  • Android

To get the free app, enter your mobile phone number.

Kindle Price: £32.03
includes VAT*
* Unlike print books, digital books are subject to VAT.

These promotions will be applied to this item:

Some promotions may be combined; others are not eligible to be combined with other offers. For details, please see the Terms & Conditions associated with these promotions.

Deliver to your Kindle or other device

Deliver to your Kindle or other device

TensorFlow Machine Learning Cookbook by [McClure, Nick]
Kindle App Ad

TensorFlow Machine Learning Cookbook Kindle Edition


See all 2 formats and editions Hide other formats and editions
Amazon Price
New from Used from
Kindle Edition
"Please retry"
£32.03

Length: 370 pages Enhanced Typesetting: Enabled Page Flip: Enabled

40 Kindle Books for £1
Browse our selection of Kindle Books discounted to £1 each. Learn more
Get a £1 reward for movies or TV
Enjoy a £1.00 reward to spend on movies or TV on Amazon Video when you purchase any Amazon Kindle Book from the Kindle Store (excluding Kindle Unlimited, Periodicals and free Kindle Books) offered by Amazon.co.uk. A maximum of 1 reward per customer applies. UK customers only. Offer ends at 23:59 on Wednesday, September 27, 2017. Terms and conditions apply

Product description

About the Author

Nick McClure

Nick McClure is currently a senior data scientist at PayScale, Inc. in Seattle, WA. Prior to this, he has worked at Zillow and Caesar's Entertainment. He got his degrees in Applied Mathematics from The University of Montana and the College of Saint Benedict and Saint John's University. He has a passion for learning and advocating for analytics, machine learning, and artificial intelligence. Nick occasionally puts his thoughts and musings on his blog, http://fromdata.org/, or through his Twitter account, @nfmcclure.


Product details

  • Format: Kindle Edition
  • File Size: 7061 KB
  • Print Length: 370 pages
  • Publisher: Packt Publishing; 1 edition (14 Feb. 2017)
  • Sold by: Amazon Media EU S.à r.l.
  • Language: English
  • ASIN: B01HY3TC54
  • Text-to-Speech: Enabled
  • X-Ray:
  • Word Wise: Not Enabled
  • Enhanced Typesetting: Enabled
  • Average Customer Review: Be the first to review this item
  • Amazon Bestsellers Rank: #237,015 Paid in Kindle Store (See Top 100 Paid in Kindle Store)
  • Would you like to tell us about a lower price?


Customer Reviews

There are no customer reviews yet on Amazon.co.uk.
5 star
4 star
3 star
2 star
1 star

Most Helpful Customer Reviews on Amazon.com (beta) (May include reviews from Early Reviewer Rewards Program)

Amazon.com: 3.5 out of 5 stars 9 reviews
8 of 8 people found the following review helpful
1.0 out of 5 stars Needs Improvement 8 Mar. 2017
By mark - Published on Amazon.com
Format: Kindle Edition Verified Purchase
It contains a lot of of good details but it lacks a lot of things.

1. The codes are not updated to Tensorflow 1.0.
2. There is no example for the Embedding Visualizer which is very important.
3. The examples are taken from the tutorial.
2 of 2 people found the following review helpful
3.0 out of 5 stars the typos are pretty bad too 23 April 2017
By Josh Li Espinoza - Published on Amazon.com
Format: Paperback Verified Purchase
The book is alright. I'm only on Chapter 2 but it's because some of the code he uses is not explained. For example, on page 33 he is using making a custom_layer function. There is a constant (A) with 2 values in it but he's not explaining where these values are coming from and it's a little confusing. Also, the typos are pretty bad too. On that same page there is a line that verbatim says: mov_avg_layer = tf.nn.conv2d(x_data, my_filter, my_strides, padding='SAME''', name='Moving_Avg_Window') like I don't know how he didn't catch the triple quotes but there a few examples of this that makes reading his code a little confusing. I payed full price $60 and am pretty disappointed.
4.0 out of 5 stars I liked it. Windows user. 26 April 2017
By William M. - Published on Amazon.com
Format: Paperback Verified Purchase
As a Windows user interested in learning to use GPUs for deep learning I have been frustrated with the available software and books for a couple of years. Most books seem to have been written on Linux systems and then you are told that the code should work fine with Windows - which is not always so. Also several deep learning systems have not been set up for Windows yet. So when I first read about TensorFlow I decided to give it a try: I got this book and one other.

Final evaluation first: I gave it 4 stars because the code worked for me (more accurately: much, not all of the code worked), but the situation was better than other books hence 4 stars. Overall, I liked the book and recommend it, it was readable and several ML algorithms were included with code and I could work around any shortcomings, like typos and other edits.

Details: as stated this book is not intended for absolute beginners. The author is quite clear about this point on page vi of the Preface. Best to have some knowledge of ML since the descriptions in the various chapters are brief. You need Python, but you don't have to be an expert, I certainly am not, but I can read existing code and make small changes, which was enough. If you are a beginner in TensorFlow Chapter 1 is not particularly right for you, more for experienced readers. (Instead, I recommend using online tutorials and/or the third chapter from the book TensorFlow for Machine Intelligence which is explanatory and well written.) Chapter 2 of this book (The TensorFlow Way) is very good, it has a creative approach: it breaks down the component parts of larger ML programs and discusses each part with code. The rest of the book is composed of chapters that include brief explanations then a lot of code. Three of the chapters are on different types of neural networks which was my main interest. I found them very helpful.

If you are a Windows user and a beginner and want to use TensorFlow with your videocard this book will be useful with some preparation. I installed everything like the following - it may not be the same for you. I got the CUDA Toolkit from Nvidia and also the deep learning supplement cuDNN (you place these files in the proper locations within the CUDA toolkit installation), I installed Python 3.5.2 (precisely, there are several comments about this on the Internet, for me 3.6.x, 3.5.1 and 3.5.3 all did not work - I don't know why.) Then the Python editor Geany. Next I installed TensorFlow using the directions on their webpage, I used the command prompt method. Lastly, several Python libraries were needed for the code in the book: numpy, scikit-learn, requests, jupyter, matplotlib and scipy.

And it all worked. So far I really like TensorFlow.
4.0 out of 5 stars Comprehensive 23 April 2017
By Adam C. Russell - Published on Amazon.com
Format: Paperback Verified Purchase
This is a solid book, and I recommend it. Like every other Packt book I've read it suffers from numerous typos, even in code sections that would result in a syntax error! Still, this is a comprehensive book and I've felt it covered most everything I wanted out of it.
4.0 out of 5 stars good book that covers a great topic 5 May 2017
By Rui Lee - Published on Amazon.com
Format: Kindle Edition Verified Purchase
good book that covers a great topic, sadly, the version is old (tf.0.12), and there are incompatibility with tf.1.1.0 in the example codes
Were these reviews helpful? Let us know
click to open popover