Incremental LLE Based on Back Propagation Neural Network

2nd International Symposium on Resource Exploration and Environmental Science

生态环境科学

Zhang, Yansheng^1,2 ; Ye, Dong^1 ; Liu, Yuanhong^2 ; Xu, Jianjun^2

School of Electrical Engineering and Automation, Harbin Institute of Technology, Harbin

150001, China^1

School of Information and Electrical Engineering, Northeast Petroleum University, Daqing, China^2

关键词: Back propagation neural networks;    Dimension reduction;    incremental LLE;    Lle algorithms;    Locally linear embedding algorithms;    Nonlinear dimensionality reduction;    Nonlinear mappings;    Synthetic datasets;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/170/4/042051/pdf
DOI  :  10.1088/1755-1315/170/4/042051

学科分类：环境科学（综合）

来源: IOP

【 摘 要 】

Locally Linear Embedding (LLE) algorithm is one of promising NonLinear Dimensionality Reduction (NLDR) method for feature extraction. Like most NLDR algorithms, LLE operates in a batch or off-line mode, in other words, for newly coming samples, the old data augmented by the new samples must be completely recalculated by LLE algorithm, which is computationally intensive. Back propagation neural network (BP) is a nonlinear mapping method, and it can learn all the information of a dataset, further, when BP is trained well, it is effective to predict new data. Hence, in this paper, BP is combined with LLE (BPLLE) to deal with out-of-sample data. Four synthetic datasets and two real datasets are given to demonstrate that BPLLE is more valid than several classical incremental LLE algorithms.