Changes for version 0.22
- XXXXXXXXX
- implemented node & layer connect methods, to allow recurrent connections.
- put sigmoid_slope function in mathlib, courtesy of frodo72 @ perlmonks
- Implemented functions to save & load snns .pat files in Dataset
- Altered Dataset constructor to allow an empty param set - you can now construct a null Dataset & add items to it using the $dataset->add([[0,1],[1]) method (also implemented in this version.
- Altered feedforward run method to return output pattern - more intuitive that way.
- There may be traces of hopfield here and there. Its WIP, but I pulled it from this release, as I was having trouble getting it to work but wanted to get the various fixes released.
- Implemented dataset->delete method.
- Put the pod documentation back in Dataset.pm :-)
Modules
A base class for implementing neural networks
a fast, pure perl backprop Neural Net simulator
support for creating/loading/saving datasets for NNFlex nets
methods for feedforward neural networks
miscellaneous mathematical functions for the AI::NNFlex NN package
A very simple experimental NN module