Class Linear

java.lang.Object
deepnetts.net.layers.activation.Linear
All Implemented Interfaces:
ActivationFunction, Serializable, Consumer<Tensor>
public final class Linear extends Object implements ActivationFunction, Serializable
Linear activation function and its derivative. Commonly used as an activation function in output layer for regression(numeric prediction) tasks. By default it passes it's input to output y = k * x where k is given as slope parameter. y = slope * x y' = slope slope parameter = 1 by default.
See Also:

  • Constructor Details

    • Linear

      public Linear()

    • Linear

      public Linear(int slope)

  • Method Details

    • getValue

      public float getValue(float x)
      Description copied from interface: ActivationFunction
      Returns the value of activation function for specified input x
      Specified by:
      getValue in interface ActivationFunction
      Parameters:
      x - input for activation
      Returns:
      value of activation function

    • getPrime

      public float getPrime(float y)
      Description copied from interface: ActivationFunction
      Returns the first derivative of activation function for specified output y
      Specified by:
      getPrime in interface ActivationFunction
      Parameters:
      y - output of activation function
      Returns:
      first derivative of activation function

    • apply

      public void apply(Tensor3D tensor, int channel)
      Specified by:
      apply in interface ActivationFunction

    • apply

      public void apply(Tensor4D tensor, int batchIdx)
      Specified by:
      apply in interface ActivationFunction

    • apply

      public void apply(Tensor tensor, int from, int to)
      Specified by:
      apply in interface ActivationFunction