Title :
Fuzzy hypersphere neural network classifier
Author :
Kulkarni, U.V. ; Sontakke, T.R.
Author_Institution :
Electron. & Comput. Sci. & Eng. Dept., SGGS Coll. of Eng. & Technol., Vishnupuri, India
fDate :
6/23/1905 12:00:00 AM
Abstract :
In this paper fuzzy hypersphere neural network (FHSNN) is proposed with its learning algorithm. The FHSNN utilizes fuzzy sets as pattern classes in which each fuzzy set is an union of fuzzy set hyperspheres. Its performance is compared with other two fuzzy neural networks and found to be superior with respect to the training time, recall time per pattern and the generalization
Keywords :
fuzzy neural nets; fuzzy set theory; learning (artificial intelligence); pattern classification; FHSNN; fuzzy hypersphere neural network classifier; fuzzy sets; generalization; learning algorithm; pattern classes; pattern classification; pattern clustering; recall time; training time; Character recognition; Clustering algorithms; Computer science; Educational institutions; Fuzzy neural networks; Fuzzy sets; Handwriting recognition; Neural networks; Neurons; Pattern classification;
Conference_Titel :
Fuzzy Systems, 2001. The 10th IEEE International Conference on
Conference_Location :
Melbourne, Vic.
Print_ISBN :
0-7803-7293-X
DOI :
10.1109/FUZZ.2001.1008961
