论文部分内容阅读
达到提出应用主成分分析法对样本进行预处理，减少网络的输入因子数，消除输入因子间的相关性并简化网络结构，达到提高网络学习速率的目的，得到的人工神经网络模型能达到所要求的精度。
It is proposed to apply the principal component analysis to preprocess the sample, reduce the number of input factors in the network, eliminate the correlation between input factors and simplify the network structure so as to achieve the goal of improving the network learning rate. The artificial neural network model obtained can meet the requirements The accuracy.