DerActFunc: Derivative of activation function of neuron

In NeuralSens: Sensitivity Analysis of Neural Networks

Derivative of activation function of neuron

Description

Evaluate derivative of activation function of a neuron

Usage

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

Arguments

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

Value

numeric output of the neuron

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)

NeuralSens documentation built on June 22, 2024, 12:06 p.m.