AI::NNFlex::backprop

• This module is the backpropagation algorithm for NNFlex. it is included in the NNFlex namespace at run time. See documentation below for standard methods.

  Copyright (c) 2004-2005 Charles Colbourn. All rights reserved. This program is free software; you can redistribute it and/or modify it under the same terms as Perl itself.

AI::NNFlex::backprop::learn

• Takes as a parameter a reference to the desired output pattern, performs one learning pass back through the network with normal backprop procedures to bring the network closer to convergence.

  This package is imported into the NNFlex namespace at runtime via a parameter to the network object.

  syntax: $network->learn([0,1,1,0]);

AI::NNFlex::backprop::learn

• learn is the main method of the backprop module. It calls calc_error to calculate the output error, calls output_adjust to adjust the weights from the last hidden to the output layer, then calls hidden_adjust to adjust the weights to the hidden layers finally it returns the network sqrd error.

AI::NNFlex::backprop::hiddenToOutput

Performs weight changes for all nodes in the output layer nodes 'connectedNodesWest' attributes, based on backprop Output weights delta

AI::NNFlex::backprop::hiddenOrInputToHidden

This subroutine calculates and applies delta weights that are not directly derived from the output layer. I.e. if you have a 2 layer network this will never get called.

If you have a 3 layer network this will be called to delta the weights between input and hidden layers.

If you have a 4 layer network it will be called to delta the weights between the two hidden layers, and the input to hidden layer

AI::NNFlex::backprop::sqrErr

• Calculates the network squared error after a single backprop pass. Internal to ::backprop