Noise Layers

Gaussian Noise

layer eddl::GaussianNoise(layer parent, float stddev, string name = "")

Apply additive zero-centered Gaussian noise.

This is useful to mitigate overfitting (you could see it as a form of random data augmentation). Gaussian Noise (GS) is a natural choice as corruption process for real valued inputs. As it is a regularization layer, it is only active at training time.

Parameters

• parent – Parent layer

• stddev – Standard deviation of the noise distribution

• name – A name for the operation

Returns

The parent after applying the GaussianNoise layer

Example:

l = GaussianNoise(l, 0.3);