ADAPTgdwm.MLPnet {AMORE}R Documentation

Adaptative on-line gradient descent with momentum single pattern training

Description

Modifies the neural network weights and biases according to one pattern chosen from the training set. Mostly written to be called by the train function so as to be applied to the whole training set. The user may choose amongst two versions of the same function: The slower ADAPTgdwm.MLPnet.R was the original R code function and ADAPTgdwm.MLPnet is the C conversed function and the one that provides higher speeds of execution.

Usage

ADAPTgdwm.MLPnet(net,Pvector,target)
ADAPTgdwm.MLPnet.R(net,Pvector,target)

Arguments

net Neural Network to train.
Pvector Input values of the training pattern.
target Output values of the training pattern.

Value

These functions return a neural network object modified according to the chosen pattern vector.

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

train


[Package AMORE version 0.2-0 Index]