Fuzzy RCE neural network

Author

Roan, Sing-Ming ; Chiang, Cheng-Chin ; Fu, Hsin-Chia

Author_Institution

Dept. of Comput. Sci. & Inf. Eng., Nat. Chiao-Tung Univ., Hsinchu, Taiwan

fYear

1993

fDate

1993

Firstpage

629

Abstract

The authors propose a supervised fuzzy neural network called a fuzzy restricted Columb energy (fuzzy RCE) network for classification problems. In a fuzzy RCE, each hidden neuron is a fuzzy prototype which can be used to represent one or many training patterns. At the learning stage, the fuzzy membership functions of prototype neurons can be automatically adjusted according to the training data. The simulation results on handwritten alphanumeric characters show that the proposed model learns very fast and has good recognition performance

Keywords

character recognition; fuzzy logic; fuzzy set theory; learning (artificial intelligence); neural nets; classification problems; fuzzy RCE neural net; fuzzy membership functions; fuzzy restricted Columb energy network; handwritten alphanumeric character recognition; learning; prototype neurons; supervised fuzzy neural network; training patterns; Character recognition; Computer science; Design engineering; Electronic mail; Fuzzy neural networks; Fuzzy sets; Neural networks; Pattern recognition; Power engineering and energy; Prototypes;

fLanguage

English

Publisher

ieee

Conference_Titel

Fuzzy Systems, 1993., Second IEEE International Conference on

Conference_Location

San Francisco, CA

Print_ISBN

0-7803-0614-7

Type

conf

DOI

10.1109/FUZZY.1993.327415

Filename

327415