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

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.

Key words: process neuron, Process Neural Network(PNN), linear interpolation function, neural network training

中图分类号: 

• TP18