Neural networks and optimization problems

A. R. Gaiduk, Yuri A. Vershinin, M. J. West

Research output: Contribution to conferencePaper

12 Citations (Scopus)

Abstract

Artificial neural networks find wide applications in control engineering, image recognition, classification and optimization of different processes. However, for the solution of high order optimization tasks, efficiency of artificial neural networks may decrease because of high growth of expenses for the development of a composite artificial neural network and, especially, for its tuning for applied tasks. This paper presents the method of decomposition of high order optimization tasks into the series of lower order tasks. This allows one to significantly speed up the solution of the tasks with application of uniform artificial neural networks of parallel action. Decomposition procedure is formed using incidence matrices and vectors in conjunction with the threshold level of intensity of interconnections in the optimization system.
Original languageEnglish
Pages37 - 41
DOIs
Publication statusPublished - 2002
EventInternational Conference on Control Applications - Glasgow, United Kingdom
Duration: 18 Sep 200220 Sep 2002

Conference

ConferenceInternational Conference on Control Applications
CountryUnited Kingdom
CityGlasgow
Period18/09/0220/09/02

Fingerprint

Neural networks
Decomposition
Image recognition
Tuning
Composite materials

Bibliographical note

The full text is not available on the repository.

Keywords

  • neural nets
  • optimal control
  • optimisation
  • parallel processing
  • decomposition
  • homogeneous neural network
  • optimization
  • parallelism
  • Artificial intelligence
  • Artificial neural networks
  • Biological neural networks
  • Control systems
  • Cost function
  • Large-scale systems
  • Matrix decomposition
  • Neural networks
  • Optimization methods
  • Radio control

Cite this

Gaiduk, A. R., Vershinin, Y. A., & West, M. J. (2002). Neural networks and optimization problems. 37 - 41. Paper presented at International Conference on Control Applications, Glasgow, United Kingdom. https://doi.org/10.1109/CCA.2002.1040156

Neural networks and optimization problems. / Gaiduk, A. R.; Vershinin, Yuri A.; West, M. J.

2002. 37 - 41 Paper presented at International Conference on Control Applications, Glasgow, United Kingdom.

Research output: Contribution to conferencePaper

Gaiduk, AR, Vershinin, YA & West, MJ 2002, 'Neural networks and optimization problems' Paper presented at International Conference on Control Applications, Glasgow, United Kingdom, 18/09/02 - 20/09/02, pp. 37 - 41. https://doi.org/10.1109/CCA.2002.1040156
Gaiduk AR, Vershinin YA, West MJ. Neural networks and optimization problems. 2002. Paper presented at International Conference on Control Applications, Glasgow, United Kingdom. https://doi.org/10.1109/CCA.2002.1040156
Gaiduk, A. R. ; Vershinin, Yuri A. ; West, M. J. / Neural networks and optimization problems. Paper presented at International Conference on Control Applications, Glasgow, United Kingdom.
@conference{4aa4546150ac425b8e8f84465b9f137a,
title = "Neural networks and optimization problems",
abstract = "Artificial neural networks find wide applications in control engineering, image recognition, classification and optimization of different processes. However, for the solution of high order optimization tasks, efficiency of artificial neural networks may decrease because of high growth of expenses for the development of a composite artificial neural network and, especially, for its tuning for applied tasks. This paper presents the method of decomposition of high order optimization tasks into the series of lower order tasks. This allows one to significantly speed up the solution of the tasks with application of uniform artificial neural networks of parallel action. Decomposition procedure is formed using incidence matrices and vectors in conjunction with the threshold level of intensity of interconnections in the optimization system.",
keywords = "neural nets, optimal control, optimisation, parallel processing, decomposition, homogeneous neural network, optimization, parallelism, Artificial intelligence, Artificial neural networks, Biological neural networks, Control systems, Cost function, Large-scale systems, Matrix decomposition, Neural networks, Optimization methods, Radio control",
author = "Gaiduk, {A. R.} and Vershinin, {Yuri A.} and West, {M. J.}",
note = "The full text is not available on the repository.; International Conference on Control Applications ; Conference date: 18-09-2002 Through 20-09-2002",
year = "2002",
doi = "10.1109/CCA.2002.1040156",
language = "English",
pages = "37 -- 41",

}

TY - CONF

T1 - Neural networks and optimization problems

AU - Gaiduk, A. R.

AU - Vershinin, Yuri A.

AU - West, M. J.

N1 - The full text is not available on the repository.

PY - 2002

Y1 - 2002

N2 - Artificial neural networks find wide applications in control engineering, image recognition, classification and optimization of different processes. However, for the solution of high order optimization tasks, efficiency of artificial neural networks may decrease because of high growth of expenses for the development of a composite artificial neural network and, especially, for its tuning for applied tasks. This paper presents the method of decomposition of high order optimization tasks into the series of lower order tasks. This allows one to significantly speed up the solution of the tasks with application of uniform artificial neural networks of parallel action. Decomposition procedure is formed using incidence matrices and vectors in conjunction with the threshold level of intensity of interconnections in the optimization system.

AB - Artificial neural networks find wide applications in control engineering, image recognition, classification and optimization of different processes. However, for the solution of high order optimization tasks, efficiency of artificial neural networks may decrease because of high growth of expenses for the development of a composite artificial neural network and, especially, for its tuning for applied tasks. This paper presents the method of decomposition of high order optimization tasks into the series of lower order tasks. This allows one to significantly speed up the solution of the tasks with application of uniform artificial neural networks of parallel action. Decomposition procedure is formed using incidence matrices and vectors in conjunction with the threshold level of intensity of interconnections in the optimization system.

KW - neural nets

KW - optimal control

KW - optimisation

KW - parallel processing

KW - decomposition

KW - homogeneous neural network

KW - optimization

KW - parallelism

KW - Artificial intelligence

KW - Artificial neural networks

KW - Biological neural networks

KW - Control systems

KW - Cost function

KW - Large-scale systems

KW - Matrix decomposition

KW - Neural networks

KW - Optimization methods

KW - Radio control

U2 - 10.1109/CCA.2002.1040156

DO - 10.1109/CCA.2002.1040156

M3 - Paper

SP - 37

EP - 41

ER -