Title :
Centroid estimation by means of uncompetitive unsupervised neural element
Author :
Acciani, G. ; Chiarantoni, E. ; Vacca, F.
Author_Institution :
Dipartimento di Elettrotecnica ed Elettronica, Politecnico di Bari, Italy
Abstract :
In this paper the drawbacks of classical unsupervised learning laws are discussed and the paradigms of an alternative clustering algorithm are carried out. Then a new model of neuron element able to search the centroid of clusters without competition with other neurons, as in an unsupervised competitive learning law, is singled out
Keywords :
neural nets; pattern recognition; unsupervised learning; centroid estimation; classical unsupervised learning law; clustering algorithm; neuron element; paradigms; uncompetitive unsupervised neural element; Artificial neural networks; Clustering algorithms; Density functional theory; Learning systems; Neurofeedback; Neurons; Unsupervised learning; Weight control;
Conference_Titel :
Circuits and Systems, 1993., Proceedings of the 36th Midwest Symposium on
Conference_Location :
Detroit, MI
Print_ISBN :
0-7803-1760-2
DOI :
10.1109/MWSCAS.1993.342997
