Package libai.nn.supervised.backpropagation

Interface Backpropagation

All Known Implementing Classes:

MomentumBackpropagation, ResilientBackpropagation, StandardBackpropagation

public interface Backpropagation

Created by kronenthaler on 08/01/2017.

Method Summary

Modifier and Type	Method	Description
void	initialize(NeuralNetwork nn, int[] nperlayer, Function[] functions, Matrix[] W, Column[] Y, Column[] b, Column[] u)	Initializes the Backpropagation algorithm with the basic structures needed.
void	train(Column[] patterns, Column[] answers, double alpha, int epochs, int offset, int length, double minerror)	Trains a neural network using the backpropagation implementaion.

Method Detail

initialize

void initialize(NeuralNetwork nn,
                int[] nperlayer,
                Function[] functions,
                Matrix[] W,
                Column[] Y,
                Column[] b,
                Column[] u)

Initializes the Backpropagation algorithm with the basic structures needed. This method usually should be called in the NeuralNetwork's train method right before calling the Backpropagation's train method.

train

void train(Column[] patterns,
           Column[] answers,
           double alpha,
           int epochs,
           int offset,
           int length,
           double minerror)

Trains a neural network using the backpropagation implementaion.