论文部分内容阅读
结合主成分分析法和神经网络的优点,提出了基于主成分分析的神经网络方法来对期货市场进行预测.引入主成分分析法对原始输入变量进行预处理,选择输入变量的主成分作为网络输入,一方面减少了输入维度,消除了各输入变量的相关性;另一方面提高了网络的收敛性和稳定性,也简化了网络的结构.通过实例验证,基于主成分的神经网络比一般神经网络训练精度更高.
Combining the advantages of principal component analysis and neural network, a neural network method based on principal component analysis is proposed to forecast the futures market.The principal component analysis is introduced to preprocess the original input variables, and the principal components of the input variables are selected as the network input On the one hand, it reduces the input dimension and eliminates the relativity of each input variable; on the other hand, it improves the convergence and stability of the network and simplifies the structure of the network.According to the example validation, the principal component-based neural network Network training accuracy is higher.