Effect of adding gaussian noise to the input layer in a CNN

Question

I often come across Keras code that adds GaussianNoise to the input, however its not clear to me what advantages does it offer to the learning.

input_img = layers.Input(t_x.shape[1:], name = 'RGB_Input') 
pp_in_layer = layers.GaussianNoise(GAUSSIAN_NOISE)(input_img)

Answer 1

Adding noise in the input data is equivalent to adding a regularization term to the objective function.

See Training with Noise is Equivalent to Tikhonov Regularization and Adding noise to the input of a model trained with a regularized objective.