Enhanced back-propagation learning and its application to business evaluation

Masaki Arisawa, Junzo Watada

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

5 Citations (Scopus)

Abstract

Layered neural networks have such several weak points in the learning algorithm of error back-propagation as terminating at a local optimal solution and requiring its learning for many hours. In this paper an enhanced method for learning algorithm is proposed in order to shorten the learning time less than a conventional method. Employing the method in a 4 bits parity check problem, its effectiveness is shown. At the end, as an application of the enhanced learning algorithm of the neural network to the real problem, the neural model of business evaluation based on financial indices is built and its efficiency of the learning was evaluated to shorten the learning time sufficiently up to 64% less than a conventional one.

Original languageEnglish
Title of host publicationIEEE International Conference on Neural Networks - Conference Proceedings
Place of PublicationPiscataway, NJ, United States
PublisherIEEE
Pages155-160
Number of pages6
Volume1
Publication statusPublished - 1994
Externally publishedYes
EventProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) - Orlando, FL, USA
Duration: 1994 Jun 271994 Jun 29

Other

OtherProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7)
CityOrlando, FL, USA
Period94/6/2794/6/29

Fingerprint

Backpropagation
Learning algorithms
Neural networks
Industry

ASJC Scopus subject areas

  • Software

Cite this

Arisawa, M., & Watada, J. (1994). Enhanced back-propagation learning and its application to business evaluation. In IEEE International Conference on Neural Networks - Conference Proceedings (Vol. 1, pp. 155-160). Piscataway, NJ, United States: IEEE.

Enhanced back-propagation learning and its application to business evaluation. / Arisawa, Masaki; Watada, Junzo.

IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 1 Piscataway, NJ, United States : IEEE, 1994. p. 155-160.

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

Arisawa, M & Watada, J 1994, Enhanced back-propagation learning and its application to business evaluation. in IEEE International Conference on Neural Networks - Conference Proceedings. vol. 1, IEEE, Piscataway, NJ, United States, pp. 155-160, Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7), Orlando, FL, USA, 94/6/27.
Arisawa M, Watada J. Enhanced back-propagation learning and its application to business evaluation. In IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 1. Piscataway, NJ, United States: IEEE. 1994. p. 155-160
Arisawa, Masaki ; Watada, Junzo. / Enhanced back-propagation learning and its application to business evaluation. IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 1 Piscataway, NJ, United States : IEEE, 1994. pp. 155-160
@inproceedings{0a5061c1c4bf4f4fa07e0eabe5201188,
title = "Enhanced back-propagation learning and its application to business evaluation",
abstract = "Layered neural networks have such several weak points in the learning algorithm of error back-propagation as terminating at a local optimal solution and requiring its learning for many hours. In this paper an enhanced method for learning algorithm is proposed in order to shorten the learning time less than a conventional method. Employing the method in a 4 bits parity check problem, its effectiveness is shown. At the end, as an application of the enhanced learning algorithm of the neural network to the real problem, the neural model of business evaluation based on financial indices is built and its efficiency of the learning was evaluated to shorten the learning time sufficiently up to 64{\%} less than a conventional one.",
author = "Masaki Arisawa and Junzo Watada",
year = "1994",
language = "English",
volume = "1",
pages = "155--160",
booktitle = "IEEE International Conference on Neural Networks - Conference Proceedings",
publisher = "IEEE",

}

TY - GEN

T1 - Enhanced back-propagation learning and its application to business evaluation

AU - Arisawa, Masaki

AU - Watada, Junzo

PY - 1994

Y1 - 1994

N2 - Layered neural networks have such several weak points in the learning algorithm of error back-propagation as terminating at a local optimal solution and requiring its learning for many hours. In this paper an enhanced method for learning algorithm is proposed in order to shorten the learning time less than a conventional method. Employing the method in a 4 bits parity check problem, its effectiveness is shown. At the end, as an application of the enhanced learning algorithm of the neural network to the real problem, the neural model of business evaluation based on financial indices is built and its efficiency of the learning was evaluated to shorten the learning time sufficiently up to 64% less than a conventional one.

AB - Layered neural networks have such several weak points in the learning algorithm of error back-propagation as terminating at a local optimal solution and requiring its learning for many hours. In this paper an enhanced method for learning algorithm is proposed in order to shorten the learning time less than a conventional method. Employing the method in a 4 bits parity check problem, its effectiveness is shown. At the end, as an application of the enhanced learning algorithm of the neural network to the real problem, the neural model of business evaluation based on financial indices is built and its efficiency of the learning was evaluated to shorten the learning time sufficiently up to 64% less than a conventional one.

UR - http://www.scopus.com/inward/record.url?scp=0028729697&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028729697&partnerID=8YFLogxK

M3 - Conference contribution

VL - 1

SP - 155

EP - 160

BT - IEEE International Conference on Neural Networks - Conference Proceedings

PB - IEEE

CY - Piscataway, NJ, United States

ER -