A computational study on the performance of artificial neural networks under changing structural design and data distribution

Research output: Contribution to journalArticle

28 Citations (Scopus)

Abstract

This paper provides the results of our computational studies on artificial neural networks (ANNs) under various structural design and data distributions. A two-group classification problem is investigated. Simulated data with varying kurtosis and variance are used to examine how the ANN performs with respect to certain structural design (size and addition of input and weight noise) characteristics. The results of our study indicate that additive noise, size, and data distribution characteristics play an important role in learning, reliability and predictive ability of ANNs.

Original languageEnglish (US)
Pages (from-to)155-177
Number of pages23
JournalEuropean Journal of Operational Research
Volume138
Issue number1
DOIs
StatePublished - Apr 1 2002

Fingerprint

Structural Design
Data Distribution
Structural design
Artificial Neural Network
Neural networks
Group Classification
Additive noise
Kurtosis
Additive Noise
Classification Problems
Artificial neural network

All Science Journal Classification (ASJC) codes

  • Modeling and Simulation
  • Management Science and Operations Research
  • Information Systems and Management

Cite this

@article{37c88347822940a58f0d9050c68495b4,
title = "A computational study on the performance of artificial neural networks under changing structural design and data distribution",
abstract = "This paper provides the results of our computational studies on artificial neural networks (ANNs) under various structural design and data distributions. A two-group classification problem is investigated. Simulated data with varying kurtosis and variance are used to examine how the ANN performs with respect to certain structural design (size and addition of input and weight noise) characteristics. The results of our study indicate that additive noise, size, and data distribution characteristics play an important role in learning, reliability and predictive ability of ANNs.",
author = "Pendharkar, {Parag C.}",
year = "2002",
month = "4",
day = "1",
doi = "10.1016/S0377-2217(01)00085-6",
language = "English (US)",
volume = "138",
pages = "155--177",
journal = "European Journal of Operational Research",
issn = "0377-2217",
publisher = "Elsevier",
number = "1",

}

TY - JOUR

T1 - A computational study on the performance of artificial neural networks under changing structural design and data distribution

AU - Pendharkar, Parag C.

PY - 2002/4/1

Y1 - 2002/4/1

N2 - This paper provides the results of our computational studies on artificial neural networks (ANNs) under various structural design and data distributions. A two-group classification problem is investigated. Simulated data with varying kurtosis and variance are used to examine how the ANN performs with respect to certain structural design (size and addition of input and weight noise) characteristics. The results of our study indicate that additive noise, size, and data distribution characteristics play an important role in learning, reliability and predictive ability of ANNs.

AB - This paper provides the results of our computational studies on artificial neural networks (ANNs) under various structural design and data distributions. A two-group classification problem is investigated. Simulated data with varying kurtosis and variance are used to examine how the ANN performs with respect to certain structural design (size and addition of input and weight noise) characteristics. The results of our study indicate that additive noise, size, and data distribution characteristics play an important role in learning, reliability and predictive ability of ANNs.

UR - http://www.scopus.com/inward/record.url?scp=0036532651&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036532651&partnerID=8YFLogxK

U2 - 10.1016/S0377-2217(01)00085-6

DO - 10.1016/S0377-2217(01)00085-6

M3 - Article

VL - 138

SP - 155

EP - 177

JO - European Journal of Operational Research

JF - European Journal of Operational Research

SN - 0377-2217

IS - 1

ER -