Ken-Soft

Software and the World

Neural Network - Load Train Data from XML - Java

Posted under Artificial Intelligence, General Development, Java, Neural Networks, Programming, Software Development by Kenny on Thursday 25 December 2008 at 9:52 pm
Bookmark and Share

This Neural Network is a command line implementation that uses the Back-Error Propagation learning algorithm. The main difference with this model is that all train data is loaded from an external XML file.
The Train data specification can be found Here.

The Zip file containing the Jar file and traindata directory can be downloaded here: NN.jar
Below is the Syntax for running NN02.jar in a command line:
java -jar NN02.jar [num center layers] [num center layer neurons] [learning rate]
An example includes:
java -jar NN02.jar 1 50 1.5
Which specifies a neural network with 1 center layers, 50 neurons per center layer, and a learning rate of 1.5. If now parameters are supplied it runs with default parameters.
Once executed, it should give a display similar to the image below.

The neural network Source is almost unchanged from a previous example found Here
Included in the zip file is my custom, and very very messy, XML Parser. If you plan on using any of this code for any real development, I recommend using a standard XML Parser. :)


No Comments »

RSS feed for comments on this post. TrackBack URI

Leave a comment

XHTML: You can use these tags: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong> <pre lang="" line="" escaped="">

Copyright © 2009 www.Ken-Soft.com