摘要
为提高多聚合过程神经网络的逼近能力和计算效率,提出一种基于数值积分的训练算法.首先将输入函数和权函数离散化,然后采用复合梯形积分或复合辛普森积分直接处理输入函数和权函数乘积的多重积分运算,采用Levenberg-Marquardt算法调整网络参数.仿真实验表明,该方法的逼近能力和计算效率比传统的正交基展开方法有明显提高,从而揭示出该方法是提高多聚合过程神经网络逼近能力和计算效率的有效途径.
To enhance approximation ability and computation efficiency of multi-aggregation process neural networks （MAPNN）, a training algorithm based on numerical integration is proposed. First, the input functions and the weight functions are discretized, and then the multi-integrations of product of input functions and weight functions are obtained by employing the combined trapezoidal integration or the combined Simpson integration. The MAPNN＇s parameters are adjusted by the Levenberg-Marquardt algorithm. The simulation results show that the approximation ability and the computation efficiency of the proposed algorithm are obviously superior to that of the orthogonal basis expansion method, which reveals that the proposed approach is an effective way to improve the approximation ablity and the computation efficiency of MAPNN.
出处
《信息与控制》
CSCD
北大核心
2013年第5期608-612,624,共6页
Information and Control
基金
国家自然科学基金资助项目(61170132)
关键词
过程神经网络
多聚合过程神经网络
数值积分
算法设计
process neural network
multi-aggregation process neural network （MAPNN）
numerical integration
algorithm design
