@frozen public struct Dropout<Scalar> : ParameterlessLayer where Scalar : TensorFlowFloatingPoint
A dropout layer.
Dropout consists in randomly setting a fraction of input units to
0 at each update during
training time, which helps prevent overfitting.
public typealias TangentVector = EmptyTangentVector
@noDerivative public let probability: Double
Creates a dropout layer.
Preconditionprobability must be a value between 0 and 1 (inclusive).
public init(probability: Double)
The probability of a node dropping out.