Abstract :
The second version of the simplified ART-based artificial neural network, named SARTNN2, is presented. The SARTNN2 model, which is made of an attentional and of an orienting subsystem, detects statistical regularities in a random sequence of multivalued input patterns. The SARTNN2 attentional subsystem consists of a flat, self-organizing Kohonen´s artificial neural network which exploits a bubble competitive strategy. Both the attentional and the orienting subsystems exploit a new metric, named normalized vector distance (NVD), which provides a normalized measurement of the intervector distance between a multivalued vector pair. The NVD measurements, which are per cent values, feature adaptability to local statistics. SARTNN2 inherits the typical KANN plasticity in addition to the peculiar ART stability. Only two user-defined parameters, both having an intuitive physical meaning, are necessary for SARTNN2 to operate. The SARTNN2 model has been tested as a clustering algorithm in the unsupervised analysis of satellite imagery
Keywords :
ART neural nets; image recognition; neural net architecture; self-organising feature maps; statistical analysis; unsupervised learning; Kohonen´s neural network; SARTNN2; bubble competitive strategy; clustering algorithm; intervector distance; normalized vector distance; self-organizing neural network; simplified ART neural network; statistical regularities; unsupervised image analysis; Artificial neural networks; Clustering algorithms; Image analysis; Merging; Neural networks; Random sequences; Stability; Statistics; Subspace constraints; Testing;
