摘要
为了研究GRNN和BPNN非线性函数的逼近能力,从数学角度详细阐述了GRNN和基于LM优化算法改进的BPNN的学习过程,编程建立了GRNN和BPNN,并分别用两种神经网络对指定的非线性函数进行逼近实验。仿真结果表明,在训练样本数量相等且中小规模网络的条件下,相对于BPNN而言,GRNN的逼近精度更高、收敛速度更快,具有很好的逼近能力,为解决非线性函数的逼近问题提供了良好的解决手段。
To study the nonlinear function approximation performances of GRNN and BPNN,the learning processes of GRNN and BPNN based on LM optimization algorithm improvement are illustrated mathematically in this paper. Then GRNN and BPNN were established with computer programming. A given nonlinear function was approximated by the two neural net-works respectively. The simulation results indicate that when the numbers of training samples are the same and the networks are small or medium-sized,GRNN has higher precision,faster convergence speed,and better approximation ability than BPNN. Thus GRNN is a good method to solve the problem of nonlinear function approximation.
出处
《现代电子技术》
2014年第7期114-117,共4页
Modern Electronics Technique
基金
国家自然科学基金(61104071)
辽宁省教育厅科学研究一般项目(L2012402)
