Search results for "distribution:AI-NNFlex AI"
AI::NNFlex - A base class for implementing neural networks
AI::NNFlex is a base class for constructing your own neural network modules. To implement a neural network, start with the documentation for AI::NNFlex::Backprop, included in this distribution...
CCOLBOURN/AI-NNFlex-0.24 - 17 Jun 2005 10:12:25 UTC
AI::NNFlex::Mathlib - miscellaneous mathematical functions for the AI::NNFlex NN package
The AI::NNFlex::Mathlib package contains activation and error functions. At present there are the following: Activation functions * tanh * linear * hopfield_threshold Error functions * atanh If you want to implement your own activation/error function...
CCOLBOURN/AI-NNFlex-0.24 - 17 Jun 2005 10:12:25 UTC
AI::NNFlex::Dataset - support for creating/loading/saving datasets for NNFlex nets
This module allows you to construct, load, save and maintain datasets for use with neural nets implemented using the AI::NNFlex classes. The dataset consists of an array of references to arrays of data. Items may be added in pairs (useful for feedfor...
CCOLBOURN/AI-NNFlex-0.24 - 17 Jun 2005 10:12:25 UTC
AI::NNFlex::Backprop - a fast, pure perl backprop Neural Net simulator
AI::NNFlex::Backprop is a class to generate feedforward, backpropagation neural nets. It inherits various constructs from AI::NNFlex & AI::NNFlex::Feedforward, but is documented here as a standalone. The code should be simple enough to use for teachi...
CCOLBOURN/AI-NNFlex-0.24 - 17 Jun 2005 10:12:25 UTC
AI::NNFlex::Hopfield - a fast, pure perl Hopfield network simulator
AI::NNFlex::Hopfield is a Hopfield network simulator derived from the AI::NNFlex class. THIS IS THE FIRST ALPHA CUT OF THIS MODULE! Any problems, let me know and I'll fix them. Hopfield networks differ from feedforward networks in that they are effec...
CCOLBOURN/AI-NNFlex-0.24 - 17 Jun 2005 10:12:25 UTC
AI::NNFlex::Reinforce - A very simple experimental NN module
Reinforce is a very simple NN module. It's mainly included in this distribution to provide an example of how to subclass AI::NNFlex to write your own NN modules. The training method strengthens any connections that are active during the run pass....
CCOLBOURN/AI-NNFlex-0.24 - 17 Jun 2005 10:12:25 UTC
AI::NNFlex::Feedforward - methods for feedforward neural networks
AI::NNFlex::Feedforward provides a run method to flow activation through an NNFlex network in west to east feedforward style....
CCOLBOURN/AI-NNFlex-0.24 - 17 Jun 2005 10:12:25 UTC