A Pattern Classifier--Modified AFC, and Handwritten Digit Recognition

Yitong ZHANG  Hideya TAKAHASHI  Kazuo SHIGETA  Eiji SHIMIZU  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E77-D   No.10   pp.1179-1185
Publication Date: 1994/10/25
Online ISSN: 
DOI: 
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Artificial Intelligence and Cognitive Science
Keyword: 
AFC algorithm,  fuzzy,  classification,  neural networks,  handwritten digit recongnition,  

Full Text: PDF>>
Buy this Article




Summary: 
We modified the adaptive fuzzy classification algorithm (AFC), which allows fuzzy clusters to grow to meet the demands of a given task during training. Every fuzzy cluster is defined by a reference vector and a fuzzy cluster radius, and it is represented as a shape of hypersphere in pattern space. Any pattern class is identified by overlapping plural hyperspherical fuzzy clusters so that it is possible to approximate complex decision boundaries among pattern classes. The modified AFC was applied to recognize handwritten digits, and performances were shown compared with other neural networks.