backpropagate.adapt.R.NeuralNet {AMORE}R Documentation

Backpropagates the single pattern error modifying accordingly the Neural Network's weights and biases.

Description

Mainly written to be called by the adapt.R.NeuralNet function. Currently two versions are available: the original R code function (backpropagate.adapt.R.NeuralNet) has kept for educational purposses while the C code version (backpropagate.adapt.C.NeuralNet) provides higher speeds of executions and thus is most likely the one to be preferred.

Usage

backpropagate.adapt.R.NeuralNet(net,target)
backpropagate.adapt.C.NeuralNet(net,target)

Arguments

net Neural Network to train.
target Training output vector.

Value

This function returns a Neural Network object with weights and biases adjusted by the adaptative backpropagation with momentum method.

Author(s)

Manuel Castejón Limas. manuel.castejon@unileon.es
Joaquin Ordieres Meré. joaquin.ordieres@dim.unirioja.es
Ana González Marcos. ana.gonzalez@unileon.es
Alpha V. Pernía Espinoza. alpha.pernia@alum.unirioja.es
Eliseo P. Vergara Gonzalez. eliseo.vergara@dim.unirioja.es
Francisco Javier Martinez de Pisón. francisco.martinez@dim.unirioja.es
Fernando Alba Elías. fernando.alba@unavarra.es

References

Simon Haykin. Neural Networks. A comprehensive foundation. 2nd Edition.

See Also

backpropagate.adapt.R.NeuralNet, adapt.R.NeuralNet, train, train.compare


[Package AMORE version 0.1.1 Index]