Evaluating the effectiveness of the fine-tuned learning enhancement to backpropagation

Steven P. Coy, Bruce L. Golden, Edward A. Wasil, George Runger

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

1 Citation (Scopus)

Abstract

Fine-tuned learning is an enhancement to the standard backpropagation algorithm that relies on the notion of data approximation followed by sequential data refinement. It appears to be a quick and accurate variant of standard backpropagation. In this paper, we conduct extensive computational testing of fine-tuned learning in order to evaluate its effectiveness in reducing processing time and avoiding early convergence to local minima. Our results show that fine-tuned learning improves the performance of standard backpropagation.

Original languageEnglish (US)
Title of host publicationIntelligent Engineering Systems Through Artificial Neural Networks
Place of PublicationFairfield, NJ, United States
PublisherASME
Pages105-111
Number of pages7
Volume7
StatePublished - 1997
Externally publishedYes
EventProceedings of the 1997 Artificial Neural Networks in Engineering Conference, ANNIE'97 - St.Louis, MO, USA
Duration: Nov 9 1997Nov 12 1997

Other

OtherProceedings of the 1997 Artificial Neural Networks in Engineering Conference, ANNIE'97
CitySt.Louis, MO, USA
Period11/9/9711/12/97

Fingerprint

Backpropagation
Backpropagation algorithms
Testing
Processing

ASJC Scopus subject areas

  • Software

Cite this

Coy, S. P., Golden, B. L., Wasil, E. A., & Runger, G. (1997). Evaluating the effectiveness of the fine-tuned learning enhancement to backpropagation. In Intelligent Engineering Systems Through Artificial Neural Networks (Vol. 7, pp. 105-111). Fairfield, NJ, United States: ASME.

Evaluating the effectiveness of the fine-tuned learning enhancement to backpropagation. / Coy, Steven P.; Golden, Bruce L.; Wasil, Edward A.; Runger, George.

Intelligent Engineering Systems Through Artificial Neural Networks. Vol. 7 Fairfield, NJ, United States : ASME, 1997. p. 105-111.

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

Coy, SP, Golden, BL, Wasil, EA & Runger, G 1997, Evaluating the effectiveness of the fine-tuned learning enhancement to backpropagation. in Intelligent Engineering Systems Through Artificial Neural Networks. vol. 7, ASME, Fairfield, NJ, United States, pp. 105-111, Proceedings of the 1997 Artificial Neural Networks in Engineering Conference, ANNIE'97, St.Louis, MO, USA, 11/9/97.
Coy SP, Golden BL, Wasil EA, Runger G. Evaluating the effectiveness of the fine-tuned learning enhancement to backpropagation. In Intelligent Engineering Systems Through Artificial Neural Networks. Vol. 7. Fairfield, NJ, United States: ASME. 1997. p. 105-111
Coy, Steven P. ; Golden, Bruce L. ; Wasil, Edward A. ; Runger, George. / Evaluating the effectiveness of the fine-tuned learning enhancement to backpropagation. Intelligent Engineering Systems Through Artificial Neural Networks. Vol. 7 Fairfield, NJ, United States : ASME, 1997. pp. 105-111
@inproceedings{aa09a3d5cf5e448392a566cd693ed78f,
title = "Evaluating the effectiveness of the fine-tuned learning enhancement to backpropagation",
abstract = "Fine-tuned learning is an enhancement to the standard backpropagation algorithm that relies on the notion of data approximation followed by sequential data refinement. It appears to be a quick and accurate variant of standard backpropagation. In this paper, we conduct extensive computational testing of fine-tuned learning in order to evaluate its effectiveness in reducing processing time and avoiding early convergence to local minima. Our results show that fine-tuned learning improves the performance of standard backpropagation.",
author = "Coy, {Steven P.} and Golden, {Bruce L.} and Wasil, {Edward A.} and George Runger",
year = "1997",
language = "English (US)",
volume = "7",
pages = "105--111",
booktitle = "Intelligent Engineering Systems Through Artificial Neural Networks",
publisher = "ASME",

}

TY - GEN

T1 - Evaluating the effectiveness of the fine-tuned learning enhancement to backpropagation

AU - Coy, Steven P.

AU - Golden, Bruce L.

AU - Wasil, Edward A.

AU - Runger, George

PY - 1997

Y1 - 1997

N2 - Fine-tuned learning is an enhancement to the standard backpropagation algorithm that relies on the notion of data approximation followed by sequential data refinement. It appears to be a quick and accurate variant of standard backpropagation. In this paper, we conduct extensive computational testing of fine-tuned learning in order to evaluate its effectiveness in reducing processing time and avoiding early convergence to local minima. Our results show that fine-tuned learning improves the performance of standard backpropagation.

AB - Fine-tuned learning is an enhancement to the standard backpropagation algorithm that relies on the notion of data approximation followed by sequential data refinement. It appears to be a quick and accurate variant of standard backpropagation. In this paper, we conduct extensive computational testing of fine-tuned learning in order to evaluate its effectiveness in reducing processing time and avoiding early convergence to local minima. Our results show that fine-tuned learning improves the performance of standard backpropagation.

UR - http://www.scopus.com/inward/record.url?scp=0031295192&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031295192&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0031295192

VL - 7

SP - 105

EP - 111

BT - Intelligent Engineering Systems Through Artificial Neural Networks

PB - ASME

CY - Fairfield, NJ, United States

ER -