AI::nnflex::reinforce

• This module is a (very experimental) reinforcement learning algorithm for nnflex. It works on the basis of a GROSS simplification of neuron activity, in that it reinforces active paths. It is 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::reinforce::learn

• Reinforces weights by activity * learning rate.

  Performs one learning pass back through the network - only currently reinforces from west to east (i.e. no reverse flow).

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

  syntax: $network->learn();