Enhanced learning in neural networks and its application to financial statement analysis

Masaki Arisawa, Junzo Watada

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

3 Citations (Scopus)

Abstract

It is discussed that layered neural networks have several weak points in the learning algorithm of error back-propagation such 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 more than a conventional method. Employing the method in a 4 bits parity check problem, its effectiveness is shown. At the end, as the application of the enhanced learning algorithm of the neural network to the real problem, the neural model for the financial statement analysis based on financial indices is discussed and its effectiveness is shown.

Original languageEnglish
Title of host publicationIEEE International Conference on Neural Networks - Conference Proceedings
Place of PublicationPiscataway, NJ, United States
PublisherIEEE
Pages3686-3692
Number of pages7
Volume6
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

Learning algorithms
Neural networks
Backpropagation

ASJC Scopus subject areas

  • Software

Cite this

Arisawa, M., & Watada, J. (1994). Enhanced learning in neural networks and its application to financial statement analysis. In IEEE International Conference on Neural Networks - Conference Proceedings (Vol. 6, pp. 3686-3692). Piscataway, NJ, United States: IEEE.

Enhanced learning in neural networks and its application to financial statement analysis. / Arisawa, Masaki; Watada, Junzo.

IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 6 Piscataway, NJ, United States : IEEE, 1994. p. 3686-3692.

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

Arisawa, M & Watada, J 1994, Enhanced learning in neural networks and its application to financial statement analysis. in IEEE International Conference on Neural Networks - Conference Proceedings. vol. 6, IEEE, Piscataway, NJ, United States, pp. 3686-3692, 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 learning in neural networks and its application to financial statement analysis. In IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 6. Piscataway, NJ, United States: IEEE. 1994. p. 3686-3692
Arisawa, Masaki ; Watada, Junzo. / Enhanced learning in neural networks and its application to financial statement analysis. IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 6 Piscataway, NJ, United States : IEEE, 1994. pp. 3686-3692
@inproceedings{9f92045e47704578afaecebed3d30dad,
title = "Enhanced learning in neural networks and its application to financial statement analysis",
abstract = "It is discussed that layered neural networks have several weak points in the learning algorithm of error back-propagation such 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 more than a conventional method. Employing the method in a 4 bits parity check problem, its effectiveness is shown. At the end, as the application of the enhanced learning algorithm of the neural network to the real problem, the neural model for the financial statement analysis based on financial indices is discussed and its effectiveness is shown.",
author = "Masaki Arisawa and Junzo Watada",
year = "1994",
language = "English",
volume = "6",
pages = "3686--3692",
booktitle = "IEEE International Conference on Neural Networks - Conference Proceedings",
publisher = "IEEE",

}

TY - GEN

T1 - Enhanced learning in neural networks and its application to financial statement analysis

AU - Arisawa, Masaki

AU - Watada, Junzo

PY - 1994

Y1 - 1994

N2 - It is discussed that layered neural networks have several weak points in the learning algorithm of error back-propagation such 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 more than a conventional method. Employing the method in a 4 bits parity check problem, its effectiveness is shown. At the end, as the application of the enhanced learning algorithm of the neural network to the real problem, the neural model for the financial statement analysis based on financial indices is discussed and its effectiveness is shown.

AB - It is discussed that layered neural networks have several weak points in the learning algorithm of error back-propagation such 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 more than a conventional method. Employing the method in a 4 bits parity check problem, its effectiveness is shown. At the end, as the application of the enhanced learning algorithm of the neural network to the real problem, the neural model for the financial statement analysis based on financial indices is discussed and its effectiveness is shown.

UR - http://www.scopus.com/inward/record.url?scp=0028694992&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028694992&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0028694992

VL - 6

SP - 3686

EP - 3692

BT - IEEE International Conference on Neural Networks - Conference Proceedings

PB - IEEE

CY - Piscataway, NJ, United States

ER -