Supervised ART-I: A new neural network architecture for learning and classifying multi-valued input patterns
A new supervised neural network architecture has been introduced, called Supervised ART-I. It has the accuracy of Fuzzy ARTMAP in classifying of both binary and analog arbitrary multi-valued input patterns. However, it is quicker in learning and classifying, has fewer parameters and requires less memory, due to its simple architecture.
The Supervised ART-I has been built from a single Fuzzy ART, instead of a pair of them as in Fuzzy ARTMAP.
During the training phase, when the tag of the winning node matches the class code, the node will be trained. If not, class correction is done. If non of the committed nodes is able to represent the input, a new node is committed and it is tagged with the current class code.
During the testing phase, if the winning node passes the vigilance parameter (\(\overline \rho \)), its tag represents the class of the input, if not the network fails to classify the current input.
The architecture, learning, and testing of the network have been discussed. The full algorithm has been listed.
KeywordsART Supervised ART Supervised learning Classification Neural Network
Unable to display preview. Download preview PDF.
- 11-.Moore, B., 1989, “ART1 and patterns clustering,” in proc. 1988 connectionist models Summer School, D. Touretzky, G. Hintoon, and T. Sejnowski, Eds, San Mateo, CA: Morgan Kaufmann, pp. 174–185.Google Scholar
- 13-.Al-Rawi, K. R., Gonzalo, C., and Arquero, A., 1999, “Supervised ART-II: A new neural network architecture, with quicker learning algorithm, for classifying multi-valued input patterns,” to be presented in the 7th conference of the European Symposium on Artificial Neural Network ESANN, Bruges, Belgium.Google Scholar
- 14-.Al-Rawi, K. R., Gonzalo, C., and Martinez, E., 1999, “Supervised ART-II for classifying Landsat TM images,” to be presented in the 19th conference of the European Association of Remote Sensing Laboratories EARSeL, LATUV, University of Valladolid, Valladolid, Spain.Google Scholar
- 15-.Al-Rawi, K. R., and Casanova, J. L., 1999, “A neural network approach for automatic monitoring of forest fires with NOAA-AVHRR imagery. Part-I: mapping burned areas,” sent for publication to the Int. J. of Remote Sensing.Google Scholar
- 16-.Al-Rawi, K. R., Casanova, J. L., and Calle, A., 1999, “A neural network approach for automatic monitoring of forest fires with NOAA-AVHRR imagery. Part-II: fires detection,” sent for publication to the Int. J. of Remote Sensing.Google Scholar