Computational neural networks

Jar-Ferr Yang, Chi Ming Chen

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we discuss an approach for designing the computational neural network, which is mainly composed of a hardlimiter neuron, a updated neuron, and a search function neuron, to solve some computational problems. The computation-by-search (CBS) scheme can effectively solve some complicated problems in the condition that their search functions can be easily obtainable by some existing neural networks. The convergence of the suggested neural networks to achieve the solution are discussed and analyzed. Both theoretical analyses and simulated results show that the proposed neural network can effectively solve the complicated computational problems such that they belong to the rational functions or their inverse functions can be easily implemented by using an existing network.

Original languageEnglish
Title of host publicationIEEE International Conference on Neural Networks - Conference Proceedings
PublisherIEEE
Pages1249-1253
Number of pages5
Volume3
Publication statusPublished - 1995
EventProceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6) - Perth, Aust
Duration: 1995 Nov 271995 Dec 1

Other

OtherProceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6)
CityPerth, Aust
Period95-11-2795-12-01

Fingerprint

Neurons
Neural networks
Rational functions

All Science Journal Classification (ASJC) codes

  • Software

Cite this

Yang, J-F., & Chen, C. M. (1995). Computational neural networks. In IEEE International Conference on Neural Networks - Conference Proceedings (Vol. 3, pp. 1249-1253). IEEE.
Yang, Jar-Ferr ; Chen, Chi Ming. / Computational neural networks. IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 3 IEEE, 1995. pp. 1249-1253
@inproceedings{8c738e38168d442c94c464abe5578920,
title = "Computational neural networks",
abstract = "In this paper, we discuss an approach for designing the computational neural network, which is mainly composed of a hardlimiter neuron, a updated neuron, and a search function neuron, to solve some computational problems. The computation-by-search (CBS) scheme can effectively solve some complicated problems in the condition that their search functions can be easily obtainable by some existing neural networks. The convergence of the suggested neural networks to achieve the solution are discussed and analyzed. Both theoretical analyses and simulated results show that the proposed neural network can effectively solve the complicated computational problems such that they belong to the rational functions or their inverse functions can be easily implemented by using an existing network.",
author = "Jar-Ferr Yang and Chen, {Chi Ming}",
year = "1995",
language = "English",
volume = "3",
pages = "1249--1253",
booktitle = "IEEE International Conference on Neural Networks - Conference Proceedings",
publisher = "IEEE",

}

Yang, J-F & Chen, CM 1995, Computational neural networks. in IEEE International Conference on Neural Networks - Conference Proceedings. vol. 3, IEEE, pp. 1249-1253, Proceedings of the 1995 IEEE International Conference on Neural Networks. Part 1 (of 6), Perth, Aust, 95-11-27.

Computational neural networks. / Yang, Jar-Ferr; Chen, Chi Ming.

IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 3 IEEE, 1995. p. 1249-1253.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Computational neural networks

AU - Yang, Jar-Ferr

AU - Chen, Chi Ming

PY - 1995

Y1 - 1995

N2 - In this paper, we discuss an approach for designing the computational neural network, which is mainly composed of a hardlimiter neuron, a updated neuron, and a search function neuron, to solve some computational problems. The computation-by-search (CBS) scheme can effectively solve some complicated problems in the condition that their search functions can be easily obtainable by some existing neural networks. The convergence of the suggested neural networks to achieve the solution are discussed and analyzed. Both theoretical analyses and simulated results show that the proposed neural network can effectively solve the complicated computational problems such that they belong to the rational functions or their inverse functions can be easily implemented by using an existing network.

AB - In this paper, we discuss an approach for designing the computational neural network, which is mainly composed of a hardlimiter neuron, a updated neuron, and a search function neuron, to solve some computational problems. The computation-by-search (CBS) scheme can effectively solve some complicated problems in the condition that their search functions can be easily obtainable by some existing neural networks. The convergence of the suggested neural networks to achieve the solution are discussed and analyzed. Both theoretical analyses and simulated results show that the proposed neural network can effectively solve the complicated computational problems such that they belong to the rational functions or their inverse functions can be easily implemented by using an existing network.

UR - http://www.scopus.com/inward/record.url?scp=0029534586&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029534586&partnerID=8YFLogxK

M3 - Conference contribution

VL - 3

SP - 1249

EP - 1253

BT - IEEE International Conference on Neural Networks - Conference Proceedings

PB - IEEE

ER -

Yang J-F, Chen CM. Computational neural networks. In IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 3. IEEE. 1995. p. 1249-1253