A threshold varying bisection method for cost sensitive learning in neural networks

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

Abstract

We propose a bisection method for varying classification threshold value for cost sensitive neural network learning. Using simulated data and different cost asymmetries, we test the proposed threshold varying bisection method and compare it with the traditional fixed-threshold method based neural network learning. The results of our experiments illustrate that the proposed threshold varying bisection method performs better than the traditional fixed-threshold method.

Original languageEnglish (US)
Title of host publicationProceedings of the International Joint Conference on Neural Networks, IJCNN 2005
Pages1039-1044
Number of pages6
DOIs
StatePublished - Dec 1 2005
EventInternational Joint Conference on Neural Networks, IJCNN 2005 - Montreal, QC, Canada
Duration: Jul 31 2005Aug 4 2005

Publication series

NameProceedings of the International Joint Conference on Neural Networks
Volume2

Other

OtherInternational Joint Conference on Neural Networks, IJCNN 2005
CountryCanada
CityMontreal, QC
Period7/31/058/4/05

Fingerprint

Neural networks
Costs
Experiments

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Cite this

Pendharkar, P. C. (2005). A threshold varying bisection method for cost sensitive learning in neural networks. In Proceedings of the International Joint Conference on Neural Networks, IJCNN 2005 (pp. 1039-1044). [1555996] (Proceedings of the International Joint Conference on Neural Networks; Vol. 2). https://doi.org/10.1109/IJCNN.2005.1555996
Pendharkar, Parag C. / A threshold varying bisection method for cost sensitive learning in neural networks. Proceedings of the International Joint Conference on Neural Networks, IJCNN 2005. 2005. pp. 1039-1044 (Proceedings of the International Joint Conference on Neural Networks).
@inproceedings{81310932300c4992998e5fda6c37eb23,
title = "A threshold varying bisection method for cost sensitive learning in neural networks",
abstract = "We propose a bisection method for varying classification threshold value for cost sensitive neural network learning. Using simulated data and different cost asymmetries, we test the proposed threshold varying bisection method and compare it with the traditional fixed-threshold method based neural network learning. The results of our experiments illustrate that the proposed threshold varying bisection method performs better than the traditional fixed-threshold method.",
author = "Pendharkar, {Parag C.}",
year = "2005",
month = "12",
day = "1",
doi = "10.1109/IJCNN.2005.1555996",
language = "English (US)",
isbn = "0780390482",
series = "Proceedings of the International Joint Conference on Neural Networks",
pages = "1039--1044",
booktitle = "Proceedings of the International Joint Conference on Neural Networks, IJCNN 2005",

}

Pendharkar, PC 2005, A threshold varying bisection method for cost sensitive learning in neural networks. in Proceedings of the International Joint Conference on Neural Networks, IJCNN 2005., 1555996, Proceedings of the International Joint Conference on Neural Networks, vol. 2, pp. 1039-1044, International Joint Conference on Neural Networks, IJCNN 2005, Montreal, QC, Canada, 7/31/05. https://doi.org/10.1109/IJCNN.2005.1555996

A threshold varying bisection method for cost sensitive learning in neural networks. / Pendharkar, Parag C.

Proceedings of the International Joint Conference on Neural Networks, IJCNN 2005. 2005. p. 1039-1044 1555996 (Proceedings of the International Joint Conference on Neural Networks; Vol. 2).

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

TY - GEN

T1 - A threshold varying bisection method for cost sensitive learning in neural networks

AU - Pendharkar, Parag C.

PY - 2005/12/1

Y1 - 2005/12/1

N2 - We propose a bisection method for varying classification threshold value for cost sensitive neural network learning. Using simulated data and different cost asymmetries, we test the proposed threshold varying bisection method and compare it with the traditional fixed-threshold method based neural network learning. The results of our experiments illustrate that the proposed threshold varying bisection method performs better than the traditional fixed-threshold method.

AB - We propose a bisection method for varying classification threshold value for cost sensitive neural network learning. Using simulated data and different cost asymmetries, we test the proposed threshold varying bisection method and compare it with the traditional fixed-threshold method based neural network learning. The results of our experiments illustrate that the proposed threshold varying bisection method performs better than the traditional fixed-threshold method.

UR - http://www.scopus.com/inward/record.url?scp=33745965459&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33745965459&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2005.1555996

DO - 10.1109/IJCNN.2005.1555996

M3 - Conference contribution

AN - SCOPUS:33745965459

SN - 0780390482

SN - 9780780390485

T3 - Proceedings of the International Joint Conference on Neural Networks

SP - 1039

EP - 1044

BT - Proceedings of the International Joint Conference on Neural Networks, IJCNN 2005

ER -

Pendharkar PC. A threshold varying bisection method for cost sensitive learning in neural networks. In Proceedings of the International Joint Conference on Neural Networks, IJCNN 2005. 2005. p. 1039-1044. 1555996. (Proceedings of the International Joint Conference on Neural Networks). https://doi.org/10.1109/IJCNN.2005.1555996