Unsupervised Learning with Dynamic Cell Structures (DCS) Neural Network

Learns data clusters and their topology in n-dimensional space using the DCS-GCS neural network.

The Dynamic Cell Structure (DCS-GCS) ANN belongs to the class of Topology Representing Networks (TRN's). It can learn supervised and unsupervised. Here, the unsupervised learning mode is implemented and demonstrated. It's learning method employs a combination of modified Kohonen learning to adjust the neuron's positions, with a sort of competitive Hebbian learning for its connections. For details please consult ref. [1]. In order to make the main script (dcs.m) functional, you must first select and generate a manifold (data) using the corresponding data generator.

REFERENCE
[1] Bruske J., Sommer G., "Dynamic Cell Structure Learns Perfectly Topology Preserving Map", Neural Computation, vol. 7, Issue 4, July 1995, pp. 845-865.