Skip to Content
R Deep Learning Essentials - Second Edition
book

R Deep Learning Essentials - Second Edition

by Mark Hodnett, Joshua F. Wiley
August 2018
Intermediate to advanced
378 pages
9h 9m
English
Packt Publishing
Content preview from R Deep Learning Essentials - Second Edition

Standardization

Another important step in data preparation is standardizing data. In the previous chapter, for the MNIST data, all pixel values were divided by 255 so that the input data was between 0.0 and 1.0. In our case, we applied min-max normalization, which transforms the data linearly using the following function:

xnew = (x-min(x))/(max(x)-min(x))

Since we already know that min(x) = 0 and max(x)=255, this reduces to the following:

xnew = x / 255.0

The other most popular form of standardization scales the feature so that the mean is 0 and the standard deviation from the mean is 1. This is also known as z-scores, and the formula for it is as follows:

xnew = (x - mean(x)) / std.dev(x)

There are three reasons why we need to perform 

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Start your free trial

You might also like

R Deep Learning Cookbook

R Deep Learning Cookbook

PKS Prakash, Achyutuni Sri Krishna Rao
Hands-On Deep Learning with R

Hands-On Deep Learning with R

Rodger Devine, Michael Pawlus
R: Unleash Machine Learning Techniques

R: Unleash Machine Learning Techniques

Raghav Bali, Dipanjan Sarkar, Brett Lantz, Cory Lesmeister
Deep Learning with R Cookbook

Deep Learning with R Cookbook

Swarna Gupta, Rehan Ali Ansari, Dipayan Sarkar

Publisher Resources

ISBN: 9781788992893Supplemental Content