摘要
针对多层前馈人工神经元网络，提出了一种多ＡＮＮ逼近策略，与单ＡＮＮ方法相比较，逼近能力、适应能力、泛化能力等都有了很大的提高．它可应用于复杂系统的建模和辨识．
This paper presents a multi ANN approximation approach to approximate complex non linear function. Compared with single ANN methods the proposed approach improves and increases the approximation and generalization ability, and adaptability greatly in learning processes of networks. The simulation results have shown that the method can be applied to the modeling and identification of complex dynamic control systems.
出处
《西安交通大学学报》
EI
CAS
CSCD
北大核心
1996年第10期16-21,36,共7页
Journal of Xi'an Jiaotong University
关键词
多ANN模型
逼近
神经网络
复杂函数
artificial neural networks multiple ANN models function approximation
