Uses of Class
dk.alexandra.fresco.stat.mlp.activationfunction.ActivationFunction

Packages that use ActivationFunction 
Package Description
dk.alexandra.fresco.stat.mlp  
dk.alexandra.fresco.stat.mlp.activationfunction  

  • Uses of ActivationFunction in dk.alexandra.fresco.stat.mlp

    Constructors in dk.alexandra.fresco.stat.mlp with parameters of type ActivationFunction 
    Constructor Description
    Layer​(double[][] weights, double[] bias, dk.alexandra.fresco.framework.builder.numeric.ProtocolBuilderNumeric inputBuilder, ActivationFunction activationFunction)
    Create a new fully connected layer with the given open weights, biases and activation function.
    Layer​(int in, int out, Random prng, dk.alexandra.fresco.framework.builder.numeric.ProtocolBuilderNumeric inputBuilder, ActivationFunction activationFunction)
    Create a new layer with random weights (bias is zero and weights are distributed as a standard Gaussian distribution divided by the number of neurons.
    Layer​(dk.alexandra.fresco.lib.common.collections.Matrix<dk.alexandra.fresco.framework.DRes<dk.alexandra.fresco.lib.fixed.SFixed>> weights, ArrayList<dk.alexandra.fresco.framework.DRes<dk.alexandra.fresco.lib.fixed.SFixed>> bias, ActivationFunction activationFunction)
    Create a new fully connected layer with the given secret weights, biases and activation function.

  • Uses of ActivationFunction in dk.alexandra.fresco.stat.mlp.activationfunction

    Methods in dk.alexandra.fresco.stat.mlp.activationfunction that return ActivationFunction 
    Modifier and Type Method Description
    static ActivationFunction ActivationFunction.valueOf​(String name)
    Returns the enum constant of this type with the specified name.
    static ActivationFunction[] ActivationFunction.values()
    Returns an array containing the constants of this enum type, in the order they are declared.
    Methods in dk.alexandra.fresco.stat.mlp.activationfunction with parameters of type ActivationFunction 
    Modifier and Type Method Description
    static dk.alexandra.fresco.framework.builder.Computation<ArrayList<dk.alexandra.fresco.framework.DRes<dk.alexandra.fresco.lib.fixed.SFixed>>,​dk.alexandra.fresco.framework.builder.numeric.ProtocolBuilderNumeric> ActivationFunction.get​(ArrayList<dk.alexandra.fresco.framework.DRes<dk.alexandra.fresco.lib.fixed.SFixed>> x, ActivationFunction type)  
    static dk.alexandra.fresco.framework.builder.Computation<ArrayList<dk.alexandra.fresco.framework.DRes<dk.alexandra.fresco.lib.fixed.SFixed>>,​dk.alexandra.fresco.framework.builder.numeric.ProtocolBuilderNumeric> ActivationFunction.getDerivative​(ArrayList<dk.alexandra.fresco.framework.DRes<dk.alexandra.fresco.lib.fixed.SFixed>> x, ArrayList<dk.alexandra.fresco.framework.DRes<dk.alexandra.fresco.lib.fixed.SFixed>> y, ActivationFunction type)
    Compute f'(x) for the given activation function f: Rn → Rn.