Home > Research > Publications & Outputs > A new model selection strategy in artificial ne...

Links

Text available via DOI:

View graph of relations

A new model selection strategy in artificial neural networks

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

A new model selection strategy in artificial neural networks. / Eǧrioǧlu, Erol; Aladaǧ, Çaǧdaş Hakan; Günay, Süleyman.
In: Applied Mathematics and Computation, Vol. 195, No. 2, 01.02.2008, p. 591-597.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Eǧrioǧlu, E, Aladaǧ, ÇH & Günay, S 2008, 'A new model selection strategy in artificial neural networks', Applied Mathematics and Computation, vol. 195, no. 2, pp. 591-597. https://doi.org/10.1016/j.amc.2007.05.005

APA

Eǧrioǧlu, E., Aladaǧ, Ç. H., & Günay, S. (2008). A new model selection strategy in artificial neural networks. Applied Mathematics and Computation, 195(2), 591-597. https://doi.org/10.1016/j.amc.2007.05.005

Vancouver

Eǧrioǧlu E, Aladaǧ ÇH, Günay S. A new model selection strategy in artificial neural networks. Applied Mathematics and Computation. 2008 Feb 1;195(2):591-597. doi: 10.1016/j.amc.2007.05.005

Author

Eǧrioǧlu, Erol ; Aladaǧ, Çaǧdaş Hakan ; Günay, Süleyman. / A new model selection strategy in artificial neural networks. In: Applied Mathematics and Computation. 2008 ; Vol. 195, No. 2. pp. 591-597.

Bibtex

@article{8374739004384863ac205d023d1321d1,
title = "A new model selection strategy in artificial neural networks",
abstract = "In recent years, artificial neural networks have been used for time series forecasting. Determining architecture of artificial neural networks is very important problem in the applications. In this study, the problem in which time series are forecasted by feed forward neural networks is examined. Various model selection criteria have been used for the determining architecture. In addition, a new model selection strategy based on well-known model selection criteria is proposed. Proposed strategy is applied to real and simulated time series. Moreover, a new direction accuracy criterion called modified direction accuracy criterion is discussed. The new model selection strategy is more reliable than known model selection criteria.",
keywords = "Artificial neural networks, Feed forward neural networks, Model selection criteria, Time series forecasting",
author = "Erol Eǧrioǧlu and Aladaǧ, {{\c C}aǧda{\c s} Hakan} and S{\"u}leyman G{\"u}nay",
year = "2008",
month = feb,
day = "1",
doi = "10.1016/j.amc.2007.05.005",
language = "English",
volume = "195",
pages = "591--597",
journal = "Applied Mathematics and Computation",
issn = "0096-3003",
publisher = "Elsevier Inc.",
number = "2",

}

RIS

TY - JOUR

T1 - A new model selection strategy in artificial neural networks

AU - Eǧrioǧlu, Erol

AU - Aladaǧ, Çaǧdaş Hakan

AU - Günay, Süleyman

PY - 2008/2/1

Y1 - 2008/2/1

N2 - In recent years, artificial neural networks have been used for time series forecasting. Determining architecture of artificial neural networks is very important problem in the applications. In this study, the problem in which time series are forecasted by feed forward neural networks is examined. Various model selection criteria have been used for the determining architecture. In addition, a new model selection strategy based on well-known model selection criteria is proposed. Proposed strategy is applied to real and simulated time series. Moreover, a new direction accuracy criterion called modified direction accuracy criterion is discussed. The new model selection strategy is more reliable than known model selection criteria.

AB - In recent years, artificial neural networks have been used for time series forecasting. Determining architecture of artificial neural networks is very important problem in the applications. In this study, the problem in which time series are forecasted by feed forward neural networks is examined. Various model selection criteria have been used for the determining architecture. In addition, a new model selection strategy based on well-known model selection criteria is proposed. Proposed strategy is applied to real and simulated time series. Moreover, a new direction accuracy criterion called modified direction accuracy criterion is discussed. The new model selection strategy is more reliable than known model selection criteria.

KW - Artificial neural networks

KW - Feed forward neural networks

KW - Model selection criteria

KW - Time series forecasting

U2 - 10.1016/j.amc.2007.05.005

DO - 10.1016/j.amc.2007.05.005

M3 - Journal article

AN - SCOPUS:37349082410

VL - 195

SP - 591

EP - 597

JO - Applied Mathematics and Computation

JF - Applied Mathematics and Computation

SN - 0096-3003

IS - 2

ER -