融入受限玻尔兹曼机的偏最小二乘优化方法

Partial Least Squares Optimization Method Integrating Restricted Boltzmann Machine

偏最小二乘法内部采用主成分分析,不能充分表达数据的非线性特征,对非线性数据的预测精度较低。为此,提出一种融合受限玻尔兹曼机与偏最小二乘的分析预测方法。该方法利用受限玻尔兹曼机对特征空间提取非线性结构,将提取的特征成分取代偏最小二乘中的成分,从而得到适应非线性的模型。实验结果表明,融合受限玻尔兹曼机与偏最小二乘法的分析方法能较好地反映数据的非线性特征。

Partial Least Squares（ PLS） method adopts Principal Component Analysis（ PCA）,it cannot express the nonlinear characteristic,and the prediction accuracy is lowin the nonlinear data. Based on this,an analysis and predicting method combining Restricted Boltzmann Machine（ RBM） with PLS is proposed. The method can extract nonlinear structure of feature space by RBMand replace the components in PLS with the extracted components,forming a model which can adapt to nonlinear dose-effect relationship. Experimental results showthat the method can well reflect the nonlinear characteristics of data.