To make training the network easier, we standardize each of the continuous variables. That is, we'll shift and scale the variables such that they have zero mean and a standard deviation of 1.
The scaling factors are saved so we can go backwards when we use the network for predictions.
SHIFTING
If we have one random variable, that is constructed by adding a constant to another random variable
- We would shift the mean by that constant
- It would not shift the standard deviation
SCALING
If we try to scale a random variable by multiplying a constant then we get a random variable
- It would effect both standard deviation and mean
I am very happy to visit your blog. This is definitely helpful to me, eagerly waiting for more updates.
ReplyDeleteData Science Training in Chennai
Data Science Course in Chennai
Data Analytics Courses in Chennai
Machine Learning Course in Chennai
Machine Learning Training in Chennai
RPA Training in Chennai
Data Science Training in Velachery
Data Science Course in Chennai
Pretty good post. I just stumbled upon your blog and wanted to say that I have really enjoyed reading your blog posts. Any way I’ll be subscribing to your feed and I hope you post again soon. The Random Blogger
ReplyDelete