Octave's Neural Network Toolbox

© by Michael Schmid
Last changes: 2007-07-27


SourceForge.net Logo

Introduction

After some years working (and correcting two errors) with the MATLAB(TM) neural network toolbox, I decided to create one for Octave. Now I'm happy about this decision because I changed my job and need a neural network toolbox but doesn't have MATLAB(TM) to work with. So actually I'm working with Octave, OctPlot and my own neural network toolbox.

You find a more detailed description of Octave's Neural Network Toolbox on this page. The bold letters are used in the unix short name of this project octnnettb for the sourceforge page.

Currently the part to commit the octnnettb code to the octave-forge repository is done. This means if you download the repository version of octave-forge you will also download the newest octnnettb.

I have to programe the complete code in my spare free time, so I'm not very fast, but one point is very important for me, testing testing and testing. So I won't release often. And this is also the reason for this simple not very stylish page ;-)

Net description:

Right now it exists only one realised neural network type. This is the multi-layer network type short MLP. This is a simple feed-forward network. So no feedback path exist. Calculation is straight forward from the input neurons to the output neurons.

Function description:

The first neural network type which will be realised is the feed-forward multi-layer perceptron. It should be possible now to use hidden layers as much as you want.
One more target is to be matlab compatible where it makes any sense!

Documentation:

No docu which makes sense to be published here. See the sourceforge server in the download section below. There you can find a User's Guide and since today a Developer's Guide.

Download:

See the sourceforge page ...

Bibliographie:

Following literature is used to build this toolbox ...