ActFunc function

Activation function of neuron

Activation function of neuron

Evaluate activation function of a neuron

ActFunc(type = "sigmoid", ...)

Arguments

  • type: character name of the activation function
  • ...: extra arguments needed to calculate the functions

Returns

numeric output of the neuron

Examples

# Return the sigmoid activation function of a neuron ActivationFunction <- ActFunc("sigmoid") # Return the tanh activation function of a neuron ActivationFunction <- ActFunc("tanh") # Return the activation function of several layers of neurons actfuncs <- c("linear","sigmoid","linear") ActivationFunctions <- sapply(actfuncs, ActFunc)

References

Pizarroso J, Portela J, Muñoz A (2022). NeuralSens: Sensitivity Analysis of Neural Networks. Journal of Statistical Software, 102(7), 1-36.

  • Maintainer: Jaime Pizarroso Gonzalo
  • License: GPL (>= 2)
  • Last published: 2024-05-11