DemoGNG DemoGNG, a Java applet, implements several methods related to competitive learning. It is possible to experiment with the methods using various data distributions and observe the learning process. A common terminology is used to make it easy to compare one method to the other. Thanks to the Java programming language the implementations run on a very large number of platforms without the need of compilation or local adaptation. Hopefully, the experimentation with the models will increase the intuitive understanding and make it easier to judge their particular strengths and weaknesses. Keywords: neural network, competitive learning, unsupervised learning, LBG, Hard Competitive Learning, Neural Gas, Competitive Hebbian Learning, Growing Neural Gas, Self-Organizing Map, Kohonen Map, Growing Grid, simulation, Voronoi diagram, Delaunay triangulation, probability distribution

Current Version:   1.3 License Type:   GPL

Home Site: http://www.neuroinformatik.ruhr-uni-bochum.de/ini/VDM/research/gsn/DemoGNG/GNG.html (online simulation) Source Code Availability:   Yes, http://www.neuroinformatik.ruhr-uni-bochum.de/ini/VDM/research/gsn/DemoGNG/DemoGNGcode.html Available Binary Packages: Debian Package:   No RedHat RPM Package:   No Other Packages:   tar.gz and zip Targeted Platforms: Where a Web browser with Java enhancements is available (It was developed under Linux (1.x.x-2.0.x) and Solaris 2 using JDK 1.0.x.) Software/Hardware Requirements: a Web browser with Java enhancements

Other Links: http://www.neuroinformatik.ruhr-uni-bochum.de/ini/PEOPLE/loos (for the most recent version) http://www.neuroinformatik.ruhr-uni-bochum.de/ini/VDM/research/gsn/DemoGNG/tex/DemoGNG/DemoGNG.html (Manual) http://www.neuroinformatik.ruhr-uni-bochum.de/ini/VDM/research/gsn/JavaPaper/ (Model Description) ftp://ftp.neuroinformatik.ruhr-uni-bochum.de/pub/software/NN/DemoGNG/ (FTP site) Mailing Lists/USENET News Groups: None User Comments: None See A Screen Shot?

  SAL Home   |   Other Scientific Fields   |   Artificial Intelligence