Application of FE-based neural networks to dynamic problems

G. Xu; G. Littlefair; R. Penson; R. Callan

doi:10.1109/ICONIP.1999.844679

Application of FE-based neural networks to dynamic problems

G. Xu, G. Littlefair, R. Penson, R. Callan

Research output: Chapter in Book/Conference paper › Conference paper › peer-review

5 Citations (Scopus)

Abstract

Firstly, finite element based neural networks (FE-based NN) are introduced with a computational energy function and a variational formulation. Then, in order to apply FE based NN to dynamic problems, the ranges of value of three main parameters in the parallel algorithm of a FE-based NN are discussed. The parameters are: descent rate, size of the time step, and weights of the derivative of the unknown variable respectively. The Taguchi method is adopted in the numeric simulation. The main results of the simulation are presented.

Original language	English
Title of host publication	ICONIP 1999, 6th International Conference on Neural Information Processing - Proceedings
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	1039-1044
Number of pages	6
Volume	3
ISBN (Electronic)	9780780358713
DOIs	https://doi.org/10.1109/ICONIP.1999.844679
Publication status	Published - 1999
Externally published	Yes
Event	6th International Conference on Neural Information Processing, ICONIP 1999 - Perth, Australia Duration: 16 Nov 1999 → 20 Nov 1999

Conference

Conference	6th International Conference on Neural Information Processing, ICONIP 1999
Country/Territory	Australia
City	Perth
Period	16/11/99 → 20/11/99

Access to Document

10.1109/ICONIP.1999.844679

Cite this

@inproceedings{93fed3a28ddc4f93bab055b04b503a40,

title = "Application of FE-based neural networks to dynamic problems",

abstract = "Firstly, finite element based neural networks (FE-based NN) are introduced with a computational energy function and a variational formulation. Then, in order to apply FE based NN to dynamic problems, the ranges of value of three main parameters in the parallel algorithm of a FE-based NN are discussed. The parameters are: descent rate, size of the time step, and weights of the derivative of the unknown variable respectively. The Taguchi method is adopted in the numeric simulation. The main results of the simulation are presented.",

keywords = "Finite Element Method, Neural Networks, Parallel Algorithm, Parameter Design",

author = "G. Xu and G. Littlefair and R. Penson and R. Callan",

note = "Publisher Copyright: {\textcopyright} 1999 IEEE.; 6th International Conference on Neural Information Processing, ICONIP 1999 ; Conference date: 16-11-1999 Through 20-11-1999",

year = "1999",

doi = "10.1109/ICONIP.1999.844679",

language = "English",

volume = "3",

pages = "1039--1044",

booktitle = "ICONIP 1999, 6th International Conference on Neural Information Processing - Proceedings",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States",

}

Xu, G, Littlefair, G, Penson, R & Callan, R 1999, Application of FE-based neural networks to dynamic problems. in ICONIP 1999, 6th International Conference on Neural Information Processing - Proceedings. vol. 3, 844679, IEEE, Institute of Electrical and Electronics Engineers, pp. 1039-1044, 6th International Conference on Neural Information Processing, ICONIP 1999, Perth, Western Australia, Australia, 16/11/99. https://doi.org/10.1109/ICONIP.1999.844679

Application of FE-based neural networks to dynamic problems. / Xu, G.; Littlefair, G.; Penson, R. et al.
ICONIP 1999, 6th International Conference on Neural Information Processing - Proceedings. Vol. 3 IEEE, Institute of Electrical and Electronics Engineers, 1999. p. 1039-1044 844679.

Research output: Chapter in Book/Conference paper › Conference paper › peer-review

TY - GEN

T1 - Application of FE-based neural networks to dynamic problems

AU - Xu, G.

AU - Littlefair, G.

AU - Penson, R.

AU - Callan, R.

PY - 1999

Y1 - 1999

N2 - Firstly, finite element based neural networks (FE-based NN) are introduced with a computational energy function and a variational formulation. Then, in order to apply FE based NN to dynamic problems, the ranges of value of three main parameters in the parallel algorithm of a FE-based NN are discussed. The parameters are: descent rate, size of the time step, and weights of the derivative of the unknown variable respectively. The Taguchi method is adopted in the numeric simulation. The main results of the simulation are presented.

AB - Firstly, finite element based neural networks (FE-based NN) are introduced with a computational energy function and a variational formulation. Then, in order to apply FE based NN to dynamic problems, the ranges of value of three main parameters in the parallel algorithm of a FE-based NN are discussed. The parameters are: descent rate, size of the time step, and weights of the derivative of the unknown variable respectively. The Taguchi method is adopted in the numeric simulation. The main results of the simulation are presented.

KW - Finite Element Method

KW - Neural Networks

KW - Parallel Algorithm

KW - Parameter Design

UR - https://www.scopus.com/pages/publications/28244438545

U2 - 10.1109/ICONIP.1999.844679

DO - 10.1109/ICONIP.1999.844679

M3 - Conference paper

AN - SCOPUS:28244438545

VL - 3

SP - 1039

EP - 1044

BT - ICONIP 1999, 6th International Conference on Neural Information Processing - Proceedings

PB - IEEE, Institute of Electrical and Electronics Engineers

T2 - 6th International Conference on Neural Information Processing, ICONIP 1999

Y2 - 16 November 1999 through 20 November 1999

ER -

Application of FE-based neural networks to dynamic problems

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this