Title :
A design algorithm of membership functions for a fuzzy neuron using example-based learning
Author :
Yamakawa, Takeshi ; Furukawa, Masuo
Author_Institution :
Kyushu Inst. of Technol., Fukuoka, Japan
Abstract :
The authors describe a design algorithm for extraction of membership functions of a fuzzy neuron based on example-based learning with optimization of cross-detecting lines. This algorithm facilitates design without the knowledge of experts. The algorithm was verified by recognition of hand-written characters. Using this algorithm, a fuzzy neuron can be designed very easily without knowledge about the features of the character, and optimum membership functions can be extracted
Keywords :
character recognition; fuzzy set theory; learning by example; neural nets; cross detecting line optimisation; example-based learning; fuzzy neuron; fuzzy set theory; handwritten character recognition; membership functions; Algorithm design and analysis; Artificial neural networks; Character recognition; Design optimization; Educational institutions; Fuzzy logic; Fuzzy systems; Hardware; Neurons; Pattern recognition;
Conference_Titel :
Fuzzy Systems, 1992., IEEE International Conference on
Conference_Location :
San Diego, CA
Print_ISBN :
0-7803-0236-2
DOI :
10.1109/FUZZY.1992.258599
