An efficient inverse ANN modeling approach using prior knowledge input with difference method

Murat Şimşek; N. Serap Şengör

doi:10.1109/ECCTD.2009.5274979

An efficient inverse ANN modeling approach using prior knowledge input with difference method

Murat Şimşek^*, N. Serap Şengör

^*Corresponding author for this work

Department of Electronics and Communication Engineering

Istanbul Technical University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

11 Citations (Scopus)

Abstract

Artificial Neural Networks (ANN) have emerged as a powerful technique for modeling. Since the embedding knowledge in ANN models is possible by the Knowledge Based ANN (KBANN) methods, more accurate results than classical ANN approach can be obtained with KBANN. Source Difference (SD), Prior Knowledge Input (PKI) and Prior Knowledge Input with Difference (PKI-D) are several methods to be mentioned which combines existing knowledge with ANN methods. The existing knowledge is obtained either by mathematical formulations, ANN modeling or measured data. The Prior Knowledge Input with Difference, which is the latest method amongst KBANN approaches is discussed in this work. We compared the response efficiency and time consumption performances of PKI-D and classical ANN methods to obtain model for Inverse Scattering Problem.

Original language	English
Title of host publication	ECCTD 2009 - European Conference on Circuit Theory and Design Conference Program
Pages	323-326
Number of pages	4
DOIs	https://doi.org/10.1109/ECCTD.2009.5274979
Publication status	Published - 2009
Event	ECCTD 2009 - European Conference on Circuit Theory and Design Conference Program - Antalya, Turkey Duration: 23 Aug 2009 → 27 Aug 2009

Publication series

Name	ECCTD 2009 - European Conference on Circuit Theory and Design Conference Program

Conference

Conference	ECCTD 2009 - European Conference on Circuit Theory and Design Conference Program
Country/Territory	Turkey
City	Antalya
Period	23/08/09 → 27/08/09

Keywords

Artificial neural networks
Inverse scattering problem
Knowledge based modeling
Prior knowledge input with difference method

Access to Document

10.1109/ECCTD.2009.5274979

Cite this

Şimşek, M., & Şengör, N. S. (2009). An efficient inverse ANN modeling approach using prior knowledge input with difference method. In ECCTD 2009 - European Conference on Circuit Theory and Design Conference Program (pp. 323-326). Article 5274979 (ECCTD 2009 - European Conference on Circuit Theory and Design Conference Program). https://doi.org/10.1109/ECCTD.2009.5274979

@inproceedings{e34a91fc0c6c4f169b92e8b6cf85db49,

title = "An efficient inverse ANN modeling approach using prior knowledge input with difference method",

abstract = "Artificial Neural Networks (ANN) have emerged as a powerful technique for modeling. Since the embedding knowledge in ANN models is possible by the Knowledge Based ANN (KBANN) methods, more accurate results than classical ANN approach can be obtained with KBANN. Source Difference (SD), Prior Knowledge Input (PKI) and Prior Knowledge Input with Difference (PKI-D) are several methods to be mentioned which combines existing knowledge with ANN methods. The existing knowledge is obtained either by mathematical formulations, ANN modeling or measured data. The Prior Knowledge Input with Difference, which is the latest method amongst KBANN approaches is discussed in this work. We compared the response efficiency and time consumption performances of PKI-D and classical ANN methods to obtain model for Inverse Scattering Problem.",

keywords = "Artificial neural networks, Inverse scattering problem, Knowledge based modeling, Prior knowledge input with difference method",

author = "Murat {\c S}im{\c s}ek and {\c S}eng{\"o}r, {N. Serap}",

year = "2009",

doi = "10.1109/ECCTD.2009.5274979",

language = "English",

isbn = "9781424438969",

series = "ECCTD 2009 - European Conference on Circuit Theory and Design Conference Program",

pages = "323--326",

booktitle = "ECCTD 2009 - European Conference on Circuit Theory and Design Conference Program",

note = "ECCTD 2009 - European Conference on Circuit Theory and Design Conference Program ; Conference date: 23-08-2009 Through 27-08-2009",

}

Şimşek, M & Şengör, NS 2009, An efficient inverse ANN modeling approach using prior knowledge input with difference method. in ECCTD 2009 - European Conference on Circuit Theory and Design Conference Program., 5274979, ECCTD 2009 - European Conference on Circuit Theory and Design Conference Program, pp. 323-326, ECCTD 2009 - European Conference on Circuit Theory and Design Conference Program, Antalya, Turkey, 23/08/09. https://doi.org/10.1109/ECCTD.2009.5274979

An efficient inverse ANN modeling approach using prior knowledge input with difference method. / Şimşek, Murat; Şengör, N. Serap.
ECCTD 2009 - European Conference on Circuit Theory and Design Conference Program. 2009. p. 323-326 5274979 (ECCTD 2009 - European Conference on Circuit Theory and Design Conference Program).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - An efficient inverse ANN modeling approach using prior knowledge input with difference method

AU - Şimşek, Murat

AU - Şengör, N. Serap

PY - 2009

Y1 - 2009

N2 - Artificial Neural Networks (ANN) have emerged as a powerful technique for modeling. Since the embedding knowledge in ANN models is possible by the Knowledge Based ANN (KBANN) methods, more accurate results than classical ANN approach can be obtained with KBANN. Source Difference (SD), Prior Knowledge Input (PKI) and Prior Knowledge Input with Difference (PKI-D) are several methods to be mentioned which combines existing knowledge with ANN methods. The existing knowledge is obtained either by mathematical formulations, ANN modeling or measured data. The Prior Knowledge Input with Difference, which is the latest method amongst KBANN approaches is discussed in this work. We compared the response efficiency and time consumption performances of PKI-D and classical ANN methods to obtain model for Inverse Scattering Problem.

AB - Artificial Neural Networks (ANN) have emerged as a powerful technique for modeling. Since the embedding knowledge in ANN models is possible by the Knowledge Based ANN (KBANN) methods, more accurate results than classical ANN approach can be obtained with KBANN. Source Difference (SD), Prior Knowledge Input (PKI) and Prior Knowledge Input with Difference (PKI-D) are several methods to be mentioned which combines existing knowledge with ANN methods. The existing knowledge is obtained either by mathematical formulations, ANN modeling or measured data. The Prior Knowledge Input with Difference, which is the latest method amongst KBANN approaches is discussed in this work. We compared the response efficiency and time consumption performances of PKI-D and classical ANN methods to obtain model for Inverse Scattering Problem.

KW - Artificial neural networks

KW - Inverse scattering problem

KW - Knowledge based modeling

KW - Prior knowledge input with difference method

UR - http://www.scopus.com/inward/record.url?scp=71249091320&partnerID=8YFLogxK

U2 - 10.1109/ECCTD.2009.5274979

DO - 10.1109/ECCTD.2009.5274979

M3 - Conference contribution

AN - SCOPUS:71249091320

SN - 9781424438969

T3 - ECCTD 2009 - European Conference on Circuit Theory and Design Conference Program

SP - 323

EP - 326

BT - ECCTD 2009 - European Conference on Circuit Theory and Design Conference Program

T2 - ECCTD 2009 - European Conference on Circuit Theory and Design Conference Program

Y2 - 23 August 2009 through 27 August 2009

ER -

An efficient inverse ANN modeling approach using prior knowledge input with difference method

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this