摘要
本文分别构建了基于RBFNN的分类模型和基于标准BPNN的分类模型,并以二维向量的模式分类为例,对所建立的2种模型进行泛化能力测试。仿真结果表明,RBFNN模型比BPNN模型具有更高的分类精度,更快的收敛速度,更适合于解决模式分类问题。
Two classification models based on Elman neural network and standard BPNN are established respectively in this paper. The classification of two dimensional vectors on a plane is taken as an example to test their generalization abilities. The simulation results show that Elman neural network has higher classification accuracy and faster convergence speed than BPNN. And it is more suitable for solving the problem of pattern classification.
出处
《电子测试》
2014年第4期41-43,共3页
Electronic Test
基金
国家自然科学基金(61104071)
关键词
RBF神经网络
BP神经网络
模式分类
收敛速度
RBF neural networks
BP neural networks
pattern classification
convergence speed
