摘要
基于样条函数逼近理论构建了以样条函数乘积为隐层神经元激励函数的三层双输入样条神经网络。该网络依据输入变量的空间结构,实现了训练数据的网格化划分,网络结构可随训练数据和网格划分数的变化进行相应调整,生成的权值矩阵做到了一步直接确定。仿真实验表明,双输入样条神经网络具有较高的建模精度,较短的运行时间,有效确定了训练数据网格划分数与网络结构的关系。
Based on the theory of spline function approximation, a three layer dual-input spline neural network model is constructed and studied, of which the hidden-layer neurons＇ activation are the product of spline function with two variables. Based on the space structure of input variable, the grid partition of training data is received. Moreover, network structure can be adjusted with the varying of the training da- ta and the mesh number, and the weight matrix can be determined directly. Simulation experiments show that dual-input spline neural network have high precision, short operation time, and the relationship be- tween the number of training data gridding partition and the network structure is determined.
出处
《中山大学学报（自然科学版）》
CAS
CSCD
北大核心
2014年第3期61-66,共6页
Acta Scientiarum Naturalium Universitatis Sunyatseni
基金
河北省自然科学基金资助项目(E2012508002)
中央高校基本科研业务费资助项目(3142013021)
河北省高等学校科学技术研究资助项目(QN20132005)
华北科技学院高等教育科学研究资助课题资助项目(HKJYZD201213)
关键词
样条函数
前馈网络
权值直接确定
网络结构
spline function
feedforward network
weights-direct-determination
network-structure
