GaussianNoise

public struct GaussianNoise<Scalar> : ParameterlessLayer where Scalar : TensorFlowFloatingPoint

GaussianNoise adds noise sampled from a normal distribution.

The noise added always has mean zero, but has a configurable standard deviation.

• TangentVector

  Declaration

  public typealias TangentVector = EmptyTangentVector

• standardDeviation

  Declaration

  @noDerivative
  public let standardDeviation: Tensor<Scalar>

• init(standardDeviation:)

  Creates a Gaussian noise layer

  Declaration

  public init(standardDeviation: Scalar)

  Parameters

  standardDeviation

  Standard deviation of the Guassian distribution

• forward(_:)

  Returns a tensor obtained by adding noise to input

  Declaration

  @differentiable
  public func forward(_ input: Tensor<Scalar>) -> Tensor<Scalar>