| 基于分段线性插值的过程神经网络训练 |
| |
| 引用本文： | 肖红,曹茂俊,李盼池,王海英.基于分段线性插值的过程神经网络训练[J].计算机工程,2011,37(20):211-212. |
| |
| 作者姓名： | 肖红 曹茂俊 李盼池 王海英 |
| |
| 作者单位： | 1. 东北石油大学计算机与信息技术学院
2. 东北石油大学计算机与信息技术学院;石油与天然气工程博士后科研流动站,黑龙江大庆163318 |
| |
| 基金项目： | 国家自然科学基金资助项目(61170132);中国博士后科学基金特别资助项目(201003405);中国博士后科学基金资助项目(20090460864);黑龙江省博士后科学基金资助项目(LBH-Z09289);黑龙江省教育厅科学技术研究基金资助项目(11551015,11551017) |
| |
| 摘 要： | 过程神经元网络的输入为时变连续函数，不能直接输入离散样本。针对该问题，提出一种基于分段线性插值函数的过程神经网络训练方法。将样本函数、过程神经元权函数的离散化数据插值为分段表示的线性函数，计算样本函数与权值函数乘积在给定采样区间上的积分，将此积分值提交给网络的隐层过程神经元，并计算网络输出。实验结果证明了该方法的有效性。
|
| 关 键 词： | 过程神经元 过程神经网络 线性插值函数 神经网络训练 |
| 收稿时间： | 2011-04-15 |
Process Neural Network Training Based on Piecewise Linear Interpolation |
| |
| XIAO Hong,CAO Mao-jun,LI Pan-chi,WANG Hai-ying.Process Neural Network Training Based on Piecewise Linear Interpolation[J].Computer Engineering,2011,37(20):211-212. |
| |
| Authors: | XIAO Hong CAO Mao-jun LI Pan-chi WANG Hai-ying |
| |
| Affiliation: | a(a.School of Computer & Information Technology;b.Post-doctoral Research Center of Oil and Gas Engineering,Northeast Petroleum University,Daqing 163318,China) |
| |
| Abstract: | Process Neural Network（PNN） can only receive time-varying continuous functions,can not receive discrete samples.To solve this problem,a training algorithm of PNN based on piecewise linear interpolation function is proposed.The discrete data of both sample functions and weight functions are transformed to piecewise linear functions,and then the integrals of product of two linear functions at a given sampling interval are computed.As a result of aggregation,these integrals are submitted to process neurons of PNN hide layer.The networks output is obtained.Experimental results show the availability of the proposed method. |
| |
| Keywords: | process neuron Process Neural Network（PNN） linear interpolation function neural network training |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程》浏览原始摘要信息 |
|
点击此处可从《计算机工程》下载全文 |
