ffnet 0.6

ffnet is meant to be an easy and fast feed-forward neural network training solution for python.
Main features:
- Any network connectivity without cycles is allowed.
- Training can be performed with use of several optimization schemes including genetic alorithm based optimization.
- There is access to exact partial derivatives of network outputs vs. its inputs.
- Automatic normalization of data.
ffnet uses some external open source software:
- networkx for handling network architecture as the graph data structure,
- numpy/scipy for training purposes,
- pikaia, genetic algorihm based oprimizer in fortran (included).
- matplotlib for plotting (examples only).
Enhancements:
- New features added in this release include an rprop training algorithm, a function for exporting a network to the Fortran subroutines, a new architecture generator, and a draft network drawing tool.