Title :
Comparative performance measures of fuzzy ARTMAP, learned vector quantization, and back propagation for handwritten character recognition
Author :
Carpenter, Gail ; Grossberg, Stephen ; Iizuka, Kunihiko
Author_Institution :
Dept. of Cognitive & Neural Syst., Boston Univ., MA, USA
Abstract :
The authors compare the performance of fuzzy ARTMAP with that of learned vector quantization and backpropagation on a handwritten character recognition task. Training with fuzzy ARTMAP to a fixed criterion used many fewer epochs. Voting with fuzzy ARTMAP yielded the highest recognition rates
Keywords :
backpropagation; character recognition; fuzzy logic; learning (artificial intelligence); vector quantisation; back propagation; fuzzy ARTMAP; handwritten character recognition; learned vector quantization; training; Adaptive systems; Character recognition; Fuzzy neural networks; Fuzzy systems; Multidimensional systems; Neural networks; Subspace constraints; Supervised learning; Vector quantization; Voting;
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
DOI :
10.1109/IJCNN.1992.287090
