Alpha Dropout is a dropout that keeps mean and variance of inputs to their original values, in order to ensure the self-normalizing property even after this dropout.
layer_alpha_dropout(object, rate, noise_shape = NULL, seed = NULL)Model or layer object
float, drop probability (as with layer_dropout()). The
multiplicative noise will have standard deviation sqrt(rate / (1 - rate)).
Noise shape
An integer to use as random seed.
Arbitrary. Use the keyword argument input_shape (list
of integers, does not include the samples axis) when using this layer as
the first layer in a model.
Same shape as input.
Alpha Dropout fits well to Scaled Exponential Linear Units by randomly setting activations to the negative saturation value.
Other noise layers: layer_gaussian_dropout,
layer_gaussian_noise