Fractional-order extreme learning machine with Levy flight

被引：1
作者：
Zhang, Shuo [1 ]
Chen, YangQuan [2 ]
Yu, Yongguang [1 ]
机构：
[1] Beijing Jiaotong Univ, Beijing 100044, Peoples R China
[2] Univ Calif Merced, Merced, CA 95343 USA
来源：
IFAC PAPERSONLINE | 2017年 / 50卷 / 01期
基金：
中国国家自然科学基金;
关键词：
Fractional-order; Extreme learning machine; Levy flight; Regression; Optimization; REGRESSION; NETWORKS; ELM;
D O I：
10.1016/j.ifacol.2017.08.1249
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
Fractional-order extreme learning machine is presented for a regression problem in this paper. The objective optimization function is designed as a fractional-order one, which can obtain better optimization results in training and testing errors. Moveover, Levy flight which is a class of fractional-order continuous random walk owing a heavy-tailed distribution, is used to search the related weight and threshold parameters. The connection between the order of Levy flight and the error result is discussed. Some given examples are provided to verify the better performance of the proposed methods. (C) 2017, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.
引用
收藏
页码：8109 / 8114
页数：6
相关论文
共 15 条
[11]  
Rao C.R., 1971, Generalized inverse of matrices and its applications, V7
[12]  
Shuai LG, 2012, I C MECH MACH VIS PR, P403
[13]   Long-Term Prediction of Time Series using NNE-based Projection and OP-ELM [J].
Sorjamaa, Antti ;
Miche, Yoan ;
Weiss, Robert ;
Lendasse, Amaury .
2008 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-8, 2008, :2674-+
[14]   Weighted least squares support vector machines: robustness and sparse approximation [J].
Suykens, JAK ;
De Brabanter, J ;
Lukas, L ;
Vandewalle, J .
NEUROCOMPUTING, 2002, 48 :85-105
[15]  
Yang X.S., 2019, Mathematical Foundations of Nature-Inspired Methods
12