Pattern classification problems involve constrained optimization in the form of minimization of chosen cost functions. Such embedded constraints in integrated neural-fuzzy pattern recognition systems improve the performance of these systems. The comparative performance of an ART-based pattern classifier integrated with fuzzy optimization constraints is demonstrated in designing vector quantizers.
|Number of pages||6|
|State||Published - 2002|
|Event||2002 International Joint Conference on Neural Networks (IJCNN'02) - Honolulu, HI, United States|
Duration: May 12 2002 → May 17 2002
|Conference||2002 International Joint Conference on Neural Networks (IJCNN'02)|
|Period||05/12/02 → 05/17/02|