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

[1] Neighborhood based Levenberg-Marquardt algorithm for neural network training
Lera, G
Pinzolas, M
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2002, 13 (05): : 1200 - 1203
[2] Backpropagation and Levenberg-Marquardt Algorithm for Training Finite Element Neural Network
Reynaldi, Arnold
Lukas, Samuel
Margaretha, Helena
2012 SIXTH UKSIM/AMSS EUROPEAN SYMPOSIUM ON COMPUTER MODELLING AND SIMULATION (EMS), 2012, : 89 - 94
[3] A quasi-local Levenberg-Marquardt algorithm for neural network training
Lera, G
Pinzolas, M
IEEE WORLD CONGRESS ON COMPUTATIONAL INTELLIGENCE, 1998, : 2242 - 2246
[4] Modified Levenberg-Marquardt Method for Neural Networks Training
Suratgar, Amir Abolfazl
Tavakoli, Mohammad Bagher
Hoseinabadi, Abbas
PROCEEDINGS OF WORLD ACADEMY OF SCIENCE, ENGINEERING AND TECHNOLOGY, VOL 6, 2005, : 46 - 48
[5] A Novel Modification on the Levenberg-Marquardt Algorithm for Avoiding Overfitting in Neural Network Training
Iplikci, Serdar
Bilgi, Batuhan
Menemen, Ali
Bahtiyar, Bedri
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2019: DEEP LEARNING, PT II, 2019, 11728 : 201 - 207
[6] Stability Analysis of the Modified Levenberg-Marquardt Algorithm for the Artificial Neural Network Training
Rubio, Jose de Jesus
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2021, 32 (08) : 3510 - 3524
[7] Performance of the Levenberg-Marquardt neural network training method in electronic nose applications
Kermani, BG
Schiffman, SS
Nagle, HT
SENSORS AND ACTUATORS B-CHEMICAL, 2005, 110 (01) : 13 - 22
[8] Adaptive Levenberg-Marquardt Algorithm: A New Optimization Strategy for Levenberg-Marquardt Neural Networks
Yan, Zhiqi
Zhong, Shisheng
Lin, Lin
Cui, Zhiquan
MATHEMATICS, 2021, 9 (17)
[9] Neural Network Training With Levenberg-Marquardt and Adaptable Weight Compression
Smith, James S.
Wu, Bo
Wilamowski, Bogdan M.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2019, 30 (02) : 580 - 587
[10] Application of the Levenberg-Marquardt method to the training of spiking neural networks
Silva, Sergio M.
Ruano, Antonio E.
2006 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORK PROCEEDINGS, VOLS 1-10, 2006, : 3978 - +

← 1 2 3 4 5 →