Question

Why it is necessary to have zero mean and unit variance in the dataset?

Answer 1

1) Using mean: By computing the mean of say, the first red pixel values across all the training images will get you the average red color value that is present across all the training images at the first position. Similarly you find this for all the red channel values, green channel values. Finally you get an average image from all the training images.

Now if you subtract this mean image from all the training images you obviously transform the pixel values of the images, the image is no longer interpretable to the human eye, the pixal values now lie in range from positive to negative where the mean lies at zero.

Answer 2

Answer:

$\LARGE{\underline{\underline{\bf{AnsweR \:  : -}}}}$

• The mean (and expected value) of a standard normal distribution is zero. Unit variance means that the standard deviation of a sample as well as the variance will tend towards 1 as the sample size tends towards infinity.