Pinball loss based extreme learning machines

2019 2nd International Conference on Advanced Materials, Intelligent Manufacturing and Automation

Wang, Kuaini^1^2 ; Ding, Xiaoshuai^3

College of Science, Xi'An Shiyou University, Xi'an, Shaanxi

710065, China^1

School of Mathematics and Research Centre for Complex Systems and Network Sciences, Southeast University, Nanjing, Jiangsu

210096, China^2

School of Education, Xizang Minzu University, Xianyang, Shaanxi

712082, China^3

关键词: Benchmark datasets;    Extreme learning machine;    Loss functions;    Machine learning methods;    Model-based OPC;    Optimization problems;    Simulated datasets;    Single-hidden layer feedforward neural networks;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/569/5/052061/pdf
DOI  :  10.1088/1757-899X/569/5/052061

来源: IOP

【 摘 要 】

Extreme Learning Machine (ELM) is a novel machine learning method by training single hidden layer feedforward neural network. It employs squared loss function to minimize the mean squares error, which is sensitive to noises and outliers. In this paper, pinball loss function with quantile error is introduced into ELM in order to improve the robustness of ELM. An ELM model based on squared pinball loss function (SPELM) and an ELM model based on pinball loss function (PELM) are proposed. The corresponding optimization problem are solved by iterative reweighted algorithm. Three simulated datasets and nine Benchmark datasets are used to verify the validity of the proposed models. It is concluded that the proposed SPELM and PELM are superior to other comparisons, especially for datasets containing larger proportion of outliers.