|
Kohonen Self Organizing Map samples
2D Organizing [Download]
This very simple application demonstrates self organizing feature of Kohonen artificial neural
networks. Initially the application creates a neural network with neurons’ weights initialized
to coordinates of points in rectangular grid. After that the network is continuously fed by
coordinates of previously generated random points. While these points are presented to the network,
it does organization of its structure. Visualizing the neural network by treating neurons’ weights
as coordinates of points shows a picture, which is close to the picture of randomly generated map,
which was fed to the network.
SOM Coloring [Download]
This application represents another sample showing self organization feature of Kohonen neural
networks and building color clusters. All network’s neurons have 3 inputs and initially 3
corresponding weights of each neuron are initialized randomly in the [0, 255] range. Weights of
each neuron may be treated as RGB tuple, which means that initially neural network represents a
rectangle of random colors. During training phase, the network is fed by random colors, which
results to network’s self organizing and forming color clusters.
Traveling Salesman Problem [Download]
The sample application shows an interesting variation of Kohonen self organizing map, which is
known as elastic net – network of neurons forming ring structure. The application uses this SOM
variant for solving Traveling Salesman Problem. Of course TSP can be better solved with
Genetic Algorithms, for example, but still this application
may be interesting as a sample of unusual SOM’a application.
|
