基于数值积分的离散过程神经网络算法及应用

为解决离散过程神经网络的训练问题，提出了两种基于数值积分的离散过程神经网络训练算法.分别采用三次样条积分和抛物插值积分直接处理离散样本和权值的时域聚合运算，采用梯度下降法实现网络参数的调整.以漫湾水电站的月径流数据预报为例，实验结果表明，两种算法性能接近，均优于基于正交基展开的过程神经网络.

Numerical integration-based discrete process neural networks algorithm and applications

To solve the training of discrete process neural networks, two training algorithms based on numerical integration were proposed. The cubic spline integration and the parabolic interpolation integration were directly applied to dealing with the aggregation of discrete samples and weights in time-domain, and the gradient descent method was employed to adjusting the networks parameters. Taking the prediction of monthly discharge of the Manwan Reservoir for example, the experimental results show that the performance of two algorithms are relatively close, and superior to the orthogonal basis-based process neural networks.