文献类型：期刊文献

中文题名：基于p阶Welsch损失的鲁棒极限学习机

英文题名：Robust Extreme Learning Machine Based on p-Power Welsch Loss

作者：陈剑挺[1];叶贞成[1];程辉[1]

机构：[1]华东理工大学化工过程先进控制和优化技术教育部重点实验室,上海200237

年份：2020

卷号：46

期号：2

起止页码：243

中文期刊名：华东理工大学学报（自然科学版）

外文期刊名：Journal of East China University of Science and Technology

收录：CSTPCD;;Scopus;北大核心:【北大核心2017】；CSCD:【CSCD_E2019_2020】；

基金：国家自然科学基金重点项目(61533003);国家自然科学基金重大项目(61590922);中央高校基本科研业务费重点科研基地创新基金(22221817014);上海市自然科学基金(17ZR1406800)。

语种：中文

中文关键词：p阶Welsch损失;极限学习机;鲁棒性;FISTA

外文关键词：p-power Welsch loss;ELM;robustness;FISTA

摘要：针对极限学习机(ELM)异常值敏感的问题,提出了一种基于p阶Welsch损失的鲁棒极限学习机。使用p阶Welsch损失代替常规ELM的均方误差损失,提高算法的鲁棒性;在目标函数中引入l1范数正则项,降低ELM网络模型的复杂度,增强模型的稳定性;采用快速迭代阈值收缩算法(FISTA)极小化目标函数,提升计算效率。对人工合成数据集和部分UCI回归数据集进行仿真,实验结果表明本文方法在鲁棒性、稳定性和训练时间上都具有很好的性能。
The conventional extreme learning machine(ELM)is sensitive to outliers.Aiming at the shortcoming,this paper proposes a robust extreme learning machine based on p-power Welsch loss.Firstly,the mean square error loss of the conventional ELM is replaced by the p-power Welsch loss to enhance the robustness of the proposed algorithm;Secondly,the l1 norm regularization is introduced into the objective function to reduce the complexity and improve the stability of the ELM network model;Moreover,a fast iterative shrinkage-thresholding algorithm(FISTA)is adopted to minimize the objective function so that the computational efficiency can be increased;Finally,the performance of the proposed method is verified by means of synthetic data and UCI datasets,which shows that the proposed algorithm can attain stronger robustness,better stability and lower training time.