Types of normalization n deep learning .

Question

Accepted Answer

Normalization in deep learning refers to scaling input data to a standard range to improve model performance.

Normalization helps in speeding up the training process by ensuring that all input features have similar scales.
Common types of normalization include min-max scaling, z-score normalization, and batch normalization.
Min-max scaling scales the data to a fixed range, typically between 0 and 1.
Z-score normalization transforms the data to have a mean of 0 and a standard deviation of 1.
Batch normalization normalizes the input of each layer by adjusting and scaling the activations.