Title :
Performance evaluation of a “parallel collision control” unsupervised neural network
Author :
Acciani, G. ; Chiarantoni, E. ; Minenna, M. ; Vacca, F.
Author_Institution :
Dipartimento di Elettrotecnica ed Elettronica, Bari Univ., Italy
Abstract :
In this paper a new neural approach to clustering tasks in handwritten numeral recognition problems is compared to classical unsupervised neural networks techniques. The kernel of the proposed network is a neural unit able to perform clustering acting alone. The network is able to find directly dense zones of the input space without requiring competition and thus overcoming the major drain backs of classical unsupervised architectures
Keywords :
character recognition; neural nets; performance evaluation; unsupervised learning; clustering; handwritten numeral recognition; parallel collision control; performance evaluation; unsupervised neural network; Character recognition; Data mining; Handwriting recognition; Kernel; Neural networks; Neurofeedback; Partitioning algorithms; Prototypes; Unsupervised learning; Vector quantization;
Conference_Titel :
Circuits and Systems, 1994., Proceedings of the 37th Midwest Symposium on
Conference_Location :
Lafayette, LA
Print_ISBN :
0-7803-2428-5
DOI :
10.1109/MWSCAS.1994.519369
