On-Line Extreme Learning Machine for Training Time-Varying Neural Networks

被引：0

作者：

Ye, Yibin ^{[1
]}

Squartini, Stefano ^{[1
]}

Piazza, Francesco ^{[1
]}

机构：

[1] Univ Politecn Marche, A3LAB, Dept Biomed Elect & Telecommun, I-60131 Ancona, Italy

来源：

BIO-INSPIRED COMPUTING AND APPLICATIONS | 2012年 / 6840卷

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Time-Varying Neural Networks(TV-NN) represent a powerful tool for nonstationary systems identification tasks, as shown in some recent works of the authors. Extreme Learning Machine approach can train TV-NNs efficiently: the reference algorithm is named ELM-TV and is of batch-learning type. In this paper, we generalize an online sequential version of ELM to TV-NN and evaluate its performances in two nonstationary systems identification tasks. The results show that our proposed algorithm produces comparable generalization performances to ELM-TV with certain benefits to those applications with sequential arrival or large number of training data.

引用

页码：49 / 54

页数：6

共 50 条

[1] An Extreme Learning Machine approach for training Time Variant Neural Networks [J].

Cingolani, Cristiano ;

Squartini, Stefano ;

Piazza, Francesco .

2008 IEEE ASIA PACIFIC CONFERENCE ON CIRCUITS AND SYSTEMS (APCCAS 2008), VOLS 1-4, 2008, :384-387

[2] TIME-VARYING NEURAL NETWORKS [J].

WALDRON, MB .

PROCEEDINGS OF THE ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY, PTS 1-4, 1988, :1933-1933

[3] On-line sequential extreme learning machine [J].

Huang, GB ;

Liang, NY ;

Rong, HJ ;

Saratchandran, R ;

Sundararajan, N .

PROCEEDINGS OF THE IASTED INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE, 2005, :232-237

[4] On-line learning from restricted training sets in multilayer neural networks [J].

Coolen, ACC ;

Saad, D ;

Xiong, YS .

EUROPHYSICS LETTERS, 2000, 51 (06) :691-697

[5] Process neural networks with time-varying inputs and outputs and learning algorithm [J].

Xu, Shao-Hua ;

He, Xin-Gui ;

Wang, Bing .

Kongzhi yu Juece/Control and Decision, 2007, 22 (12) :1425-1428

[6] Continual on-line training of neural networks with applications to electric machine fault diagnostics [J].

Tallam, RM ;

Habetler, TG ;

Harley, RG .

PESC 2001: 32ND ANNUAL POWER ELECTRONICS SPECIALISTS CONFERENCE, VOLS 1-4, CONFERENCE PROCEEDINGS, 2001, :2224-2228

[7] Online Spatiotemporal Extreme Learning Machine for Complex Time-Varying Distributed Parameter Systems [J].

Lu, Xinjiang ;

Yin, Feng ;

Liu, Chang ;

Huang, Minghui .

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2017, 13 (04) :1753-1762

[8] On-line state detection in time-varying traffic patterns [J].

Moltchanov, D. .

NEXT GENERATION TELETRAFFIC AND WIRED/WIRELESS ADVANCED NETWORKING, PROCEEDINGS, 2007, 4712 :49-+

[9] Adaptive control of rapidly time-varying discrete -time system using initial-training-free online extreme learning machine [J].

Gao, Xiang Hui ;

Wong, Ka In ;

Wong, Pak Kin ;

Vong, Chi Man .

NEUROCOMPUTING, 2016, 194 :117-125

[10] An improved on-line sequential learning algorithm for extreme learning machine [J].

Li, Bin ;

Wang, Jingming ;

Li, Yibin ;

Song, Yong .

ADVANCES IN NEURAL NETWORKS - ISNN 2007, PT 1, PROCEEDINGS, 2007, 4491 :1087-+

← 1 2 3 4 5 →