Variable projection method and levenberg-marquardt algorithm for neural network training

被引：0

作者：

Kim, Cheol-Taek ^{[1
]}

Lee, Ju-Jang ^{[1
]}

Kim, Hyejin ^{[2
]}

机构：

[1] Korea Adv Inst Sci & Technol, 373-1,Kuseongdong, Taejon 305701, South Korea

[2] ETRI, Taejon, South Korea

来源：

IECON 2006 - 32ND ANNUAL CONFERENCE ON IEEE INDUSTRIAL ELECTRONICS, VOLS 1-11 | 2006年

关键词：

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

An optimal solution for single hidden layered feedforward neural network(SLFN) is proposed. SLFN can be considered as separable nonlinear least squares problem and variable projection(VP) method gives the approximation of the jacobian matrix of the problem. The jacobian calculation of VP-SLFN is suggested with simplified form. Based on this simplification, Levenberg-Marquardt(LM) algorithm for VP-SLFN is suggested and has faster convergence rate than LM algorithm without VP. Two numerical examples show the superiority than extreme learning machine and LM without variable projection.

引用

页码：2084 / +

页数：2

共 50 条

[31] Neural network predictive control for dissolved oxygen based on levenberg-marquardt algorithm
Li M.
Zhou L.
Wang J.
Nongye Jixie Xuebao, 6 (297-302): : 297 - 302
[32] Adding Nonlinear System Dynamics to Levenberg-Marquardt Algorithm for Neural Network Control
Larrea, Mikel
Irigoyen, Eloy
Gomez, Vicente
ARTIFICIAL NEURAL NETWORKS (ICANN 2010), PT III, 2010, 6354 : 352 - 357
[33] Application of BP Neural Network Based on Levenberg-Marquardt Algorithm in Appraisal Analysis
He Houfeng
Wang Baoguo
PROCEEDINGS OF THE 9TH CONFERENCE ON MAN-MACHINE-ENVIRONMENT SYSTEM ENGINEERING, 2009, : 266 - 270
[34] An echo state network based on Levenberg-Marquardt algorithm
Wang, Lei
Yang, Cuili
Qiao, Junfei
Wang, Gongming
PROCEEDINGS OF THE 36TH CHINESE CONTROL CONFERENCE (CCC 2017), 2017, : 3899 - 3904
[35] On-line training of neural networks: A sliding window approach for the Levenberg-Marquardt algorithm
Dias, FM
Antunes, A
Vieira, J
Mota, AM
ARTIFICIAL INTELLIGENCE AND KNOWLEDGE ENGINEERING APPLICATIONS: A BIOINSPIRED APPROACH, PT 2, PROCEEDINGS, 2005, 3562 : 577 - 585
[36] Optimization of projection matrix between cameras based on Levenberg-Marquardt algorithm
Zhang, Lei
Zheng, Shubin
Chai, Xiaodong
Xu, Qingxia
Zi, Anqi
Journal of Information and Computational Science, 2015, 12 (04): : 1607 - 1614
[37] Recursive Bayesian Levenberg-Marquardt training of recurrent neural networks
Mirikitani, Derrick
Nikolaev, Nikolay
2007 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-6, 2007, : 282 - 287
[38] Improved Computation for Levenberg-Marquardt Training
Wilamowski, Bogdan M.
Yu, Hao
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2010, 21 (06): : 930 - 937
[39] Levenberg-Marquardt training for modular networks
Fun, MH
Hagan, MT
ICNN - 1996 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS. 1-4, 1996, : 468 - 473
[40] Optimisation Using Levenberg-Marquardt Algorithm of Neural Networks for Iris
Sayed, Asim
Sardeshmukh, M.
Limkar, Suresh
PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON FRONTIERS OF INTELLIGENT COMPUTING: THEORY AND APPLICATIONS (FICTA) 2013, 2014, 247 : 91 - 98

← 1 2 3 4 5 →