Application of evolutionary programming and probabilistic neural networks to breast cancer diagnosis

Joseph Y. Lo, Walker H. Land, Clayton T Morrison

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

4 Citations (Scopus)

Abstract

Two novel artificial neural network techniques, evolutionary programming (EP) and probabilistic neural networks (PNN), were applied to the problem of breast cancer diagnosis. The EP is a stochastic optimization technique with the ability to mutate both network connections and weight values. The PNN has the ability to produce optimal Bayesian decision making given sufficient training data. Both techniques offer potential improvements over the well-studied, classic backpropagation networks. Preliminary performances of these new techniques were comparable to but slightly worse than the classic networks. In on-going work, these new techniques will be optimized further and should produce results greater than or equal to the classic networks, but with more information content and confidence.

Original languageEnglish (US)
Title of host publicationProceedings of the International Joint Conference on Neural Networks
PublisherIEEE
Pages3712-3716
Number of pages5
Volume5
StatePublished - 1999
Externally publishedYes
EventInternational Joint Conference on Neural Networks (IJCNN'99) - Washington, DC, USA
Duration: Jul 10 1999Jul 16 1999

Other

OtherInternational Joint Conference on Neural Networks (IJCNN'99)
CityWashington, DC, USA
Period7/10/997/16/99

Fingerprint

Evolutionary algorithms
Neural networks
Backpropagation
Decision making

ASJC Scopus subject areas

  • Software

Cite this

Lo, J. Y., Land, W. H., & Morrison, C. T. (1999). Application of evolutionary programming and probabilistic neural networks to breast cancer diagnosis. In Proceedings of the International Joint Conference on Neural Networks (Vol. 5, pp. 3712-3716). IEEE.

Application of evolutionary programming and probabilistic neural networks to breast cancer diagnosis. / Lo, Joseph Y.; Land, Walker H.; Morrison, Clayton T.

Proceedings of the International Joint Conference on Neural Networks. Vol. 5 IEEE, 1999. p. 3712-3716.

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

Lo, JY, Land, WH & Morrison, CT 1999, Application of evolutionary programming and probabilistic neural networks to breast cancer diagnosis. in Proceedings of the International Joint Conference on Neural Networks. vol. 5, IEEE, pp. 3712-3716, International Joint Conference on Neural Networks (IJCNN'99), Washington, DC, USA, 7/10/99.
Lo JY, Land WH, Morrison CT. Application of evolutionary programming and probabilistic neural networks to breast cancer diagnosis. In Proceedings of the International Joint Conference on Neural Networks. Vol. 5. IEEE. 1999. p. 3712-3716
Lo, Joseph Y. ; Land, Walker H. ; Morrison, Clayton T. / Application of evolutionary programming and probabilistic neural networks to breast cancer diagnosis. Proceedings of the International Joint Conference on Neural Networks. Vol. 5 IEEE, 1999. pp. 3712-3716
@inproceedings{f9a886c343af417cbc2fe4d5f492e670,
title = "Application of evolutionary programming and probabilistic neural networks to breast cancer diagnosis",
abstract = "Two novel artificial neural network techniques, evolutionary programming (EP) and probabilistic neural networks (PNN), were applied to the problem of breast cancer diagnosis. The EP is a stochastic optimization technique with the ability to mutate both network connections and weight values. The PNN has the ability to produce optimal Bayesian decision making given sufficient training data. Both techniques offer potential improvements over the well-studied, classic backpropagation networks. Preliminary performances of these new techniques were comparable to but slightly worse than the classic networks. In on-going work, these new techniques will be optimized further and should produce results greater than or equal to the classic networks, but with more information content and confidence.",
author = "Lo, {Joseph Y.} and Land, {Walker H.} and Morrison, {Clayton T}",
year = "1999",
language = "English (US)",
volume = "5",
pages = "3712--3716",
booktitle = "Proceedings of the International Joint Conference on Neural Networks",
publisher = "IEEE",

}

TY - GEN

T1 - Application of evolutionary programming and probabilistic neural networks to breast cancer diagnosis

AU - Lo, Joseph Y.

AU - Land, Walker H.

AU - Morrison, Clayton T

PY - 1999

Y1 - 1999

N2 - Two novel artificial neural network techniques, evolutionary programming (EP) and probabilistic neural networks (PNN), were applied to the problem of breast cancer diagnosis. The EP is a stochastic optimization technique with the ability to mutate both network connections and weight values. The PNN has the ability to produce optimal Bayesian decision making given sufficient training data. Both techniques offer potential improvements over the well-studied, classic backpropagation networks. Preliminary performances of these new techniques were comparable to but slightly worse than the classic networks. In on-going work, these new techniques will be optimized further and should produce results greater than or equal to the classic networks, but with more information content and confidence.

AB - Two novel artificial neural network techniques, evolutionary programming (EP) and probabilistic neural networks (PNN), were applied to the problem of breast cancer diagnosis. The EP is a stochastic optimization technique with the ability to mutate both network connections and weight values. The PNN has the ability to produce optimal Bayesian decision making given sufficient training data. Both techniques offer potential improvements over the well-studied, classic backpropagation networks. Preliminary performances of these new techniques were comparable to but slightly worse than the classic networks. In on-going work, these new techniques will be optimized further and should produce results greater than or equal to the classic networks, but with more information content and confidence.

UR - http://www.scopus.com/inward/record.url?scp=0033326220&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033326220&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0033326220

VL - 5

SP - 3712

EP - 3716

BT - Proceedings of the International Joint Conference on Neural Networks

PB - IEEE

ER -