Universal approximation of polygonal fuzzy neural networks in sense of K-integral norms
Universal approximation of polygonal fuzzy neural networks in sense of K-integral norms作者机构：School of Mathematics Science Tianjin Normal University Tianjin China School of Management Tianjin Normal University Tianjin China
出 版 物：《Science China(Information Sciences)》 (中国科学:信息科学(英文版))
年 卷 期：2011年第54卷第11期
页 面：2307-2323页
核心收录：
学科分类：0810[工学-信息与通信工程] 12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 0808[工学-电气工程] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）]
基 金：supported by the National Natural Science Foundation of China (Grant No. 60974144)
主 题：polygonal fuzzy numbers K-quasi-additive integrals K-integral norms polygonal fuzzy neural networks universal approximations
摘 要：In this paper,we introduce polygonal fuzzy numbers to overcome the operational complexity of ordinary fuzzy numbers,and obtain two important inequalities by taking advantage of their fine *** presenting an actual example,we demonstrate that the approximation capability of polygonal fuzzy numbers is ***,the concepts of K-quasi-additive integrals and K-integral norms are *** the polygonal fuzzy numbers space satisfies separability,the density problems for several functions spaces can be studied,by means of fuzzy-valued simple functions and fuzzy-valued Bernstein *** establish that the class of the integrally-bounded fuzzy-valued functions spans a complete and separable metric space in the K-integral ***,in the sense of K-integral norms,the universal approximation of fourlayer regular polygonal fuzzy neural networks for fuzzy-valued simple functions is ***,we show that this type of networks also possesses universal approximation for the class of integrally-bounded fuzzyvalued *** result indicates that the approximation capability which regular polygonal fuzzy neural networks for continuous fuzzy systems can be extended as for general integrable systems.
同方期刊数据库