Batch Normalization in Deep Neural Networks - KDnuggets

Normalization is a procedure to change the value of the numeric variable in the dataset to a typical scale, without misshaping contrasts in the range of value. In deep learning, preparing a deep neural network with many layers as they can be delicate to the underlying initial random weights and design of the learning algorithm. One potential purpose behind this trouble is the distribution of the inputs to layers somewhere down in the network may change after each mini-batch when the weights are refreshed. This can make the learning algorithm always pursue a moving target. This adjustment in the distribution of inputs to layers in the network has alluded to the specialized name internal covariate shift.