Dispensability of bias for three-layer max-min fuzzy neural networks

被引：0
作者：
Yang, Jie [1 ]
Li, Long [2 ]
机构：
[1] Dalian Univ Technol, Sch Elect & Informat Engn, Dalian, Peoples R China
[2] Dalian Univ Technol, Dept Appl Math, Dalian, Peoples R China
来源：
ICNC 2007: THIRD INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION, VOL 1, PROCEEDINGS | 2007年
基金：
中国国家自然科学基金;
关键词：
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
It is well-known that a conventional feedforward neural network always has bias (threshold) terms, which is necessary for it to solve classification or approximation problems. But for fuzzy neural networks (FNNs), it seems not quite clear yet whether the bias is dispensable or not. Some authors introduce the bias, while the others do not. We consider a three layers max-min FNNs, and prove that the bias indeed can be useless in certain cases specified in this paper.
引用
收藏
页码：135 / +
页数：2
相关论文
共 50 条
12345