一种基于分类问题的光滑极限学习机A Smooth Extreme Learning Machine for Classification
杨丽明,张思韫,任卓
摘要(Abstract)：
极限学习机具有快速的学习速度和良好的泛化性能.光滑化是一种重要的处理非光滑问题的技术.将光滑化技术应用于极限学习机,提出了一种光滑化的极限学习机框架,并用Newton-Armijo算法来求解.该算法具有全局和二次收敛的性质.与已有的光滑支持向量机相比,该模型有更少的决策变量,并且能够更好地解决非线性问题.数值实验表明该算法的速度要比传统的极限学习算法更快.与支持向量机相比,提出的算法有更好的或者相似的泛化性能.
关键词(KeyWords)： 极限学习机;光滑化方法;Newton-Armijo算法;神经网络
基金项目(Foundation): 国家自然科学基金资助项目(11471010)
作者(Author): 杨丽明,张思韫,任卓
DOI: 10.13705/j.issn.1671-6841.2016097
参考文献(References)：
- [1]HUANG G B,SIEW C K,ZHU Q Y.Extreme learning machine:theory and applications[J].Neurocomputing,2006,70(1/2/3):489-501.
- [2]HUANG G B,DING X,ZHOU H.Optimization method based extreme learning machine for classification[J].Neurocomputing,2010,74(1/2/3):155-163.
- [3]MATIAS T,SOUZA F,ARAUJO R,et al.Learning of a single-hidden layer feedforward neural network using an optimized extreme learning machine[J].Neurocomputing,2014,129(10):428-436.
- [4]LIU X Y,GAO C H,LI P.A comparative analysis of support vector machines and extreme learning machines[J].Neural networks,2012,33(9):58-66.
- [5]魏培文,段德全,孙印杰,等.基于SVM的生物医学事件触发词识别研究[J].信阳师范学院学报(自然科学版),2015,28(3):446-449.
- [6]ALABDULMOHSIN I,MOUSTAPHA C,GAO X,et al.Large margin classification with indefinite similarities[J].Machine learning,2016,103(2):215-237.
- [7]CHEN C,MANGASARIAN O L.A class of smoothing functions for nonlinear and mixed complementarity problems[J].Computational optimization and applications,1996,5(2):97-138.
- [8]CHEN X J,DU S Q,ZHOU Y.A smoothing trust region filter algorithm for nonsmooth least squares problems[J].Science China-mathematics,2014,59(5):999-1014.
- [9]BALASUNDARAM S,KAPIL D G.1-norm extreme learning machine for regression and multiclass classification using Newton method[J].Neurocomputing,2014,128(2):4-14.
- [10]王小朋,刘翔峰.一种基于病态问题的修正牛顿法[J].河南科技大学学报(自然科学版),2015,36(1):86-91.
- [11]LEE Y J,MANGASARIAN O L.SSVM:a smooth support vector machine[J].Computational optimization and applications,2001,20(1):5-22.
- [12]TRIPATHY A,AGRAWAL A,RATH S K.Classification of sentiment reviews using n-gram machine learning approach[J].Expert systems with applications,2016,57(15):117-126.
- [13]LIU Q,HE Q,SHI Z.Extreme support vector machine classifier[C]//Procceedings of the 12th Pacific-Asia conference on advances in knowledge discovery and data mining.Berlin,2008.