NeuralSens (version 1.1.3)

DerActFunc: Derivative of activation function of neuron

Description

Evaluate derivative of activation function of a neuron

Usage

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

Value

numeric output of the neuron

Arguments

type

character name of the activation function

...

extra arguments needed to calculate the functions

References

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

Examples

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