public class RMSProp<Model: Layer, Scalar: TensorFlowFloatingPoint>: Optimizer
    where Model.AllDifferentiableVariables == Model.CotangentVector

RMSProp optimizer.

It is recommended to leave the parameters of this optimizer at their default values (except the learning rate, which can be freely tuned). This optimizer is usually a good choice for recurrent neural networks.

Reference: rmsprop: Divide the gradient by a running average of its recent magnitude

  • The learning rate.

    Declaration

    public let learningRate: Scalar
  • rho

    Declaration

    public let rho: Scalar
  • A small scalar added to the denominator to improve numerical stability.

    Declaration

    public let epsilon: Scalar
  • The weight decay.

    Declaration

    public let decay: Scalar
  • Declaration

    public init(
        learningRate: Scalar = 0.001,
        rho: Scalar = 0.9,
        epsilon: Scalar = 1e-8,
        decay: Scalar = 0
    )
  • Declaration

    public convenience init(
        for _: __shared Model,
        learningRate: Scalar = 0.001,
        rho: Scalar = 0.9,
        epsilon: Scalar = 1e-8,
        decay: Scalar = 0,
        scalarType: Scalar.Type
    )
  • Declaration

    public func update(_ model: inout Model.AllDifferentiableVariables,
                       along direction: Model.CotangentVector)