An information geometric approach to survival analysis and feature selection by neural networks

Antonio Eleuteri, Roberta Tagliaferri, Leopoldo Milano, Michele De Laurentiis

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

Abstract

In this paper an information geometric approach to survival analysis is described. It is shown how a neural network can be used to model the probability of failure of a system, and how it can be trained by minimising a suitable divergence functional in a Bayesian framework. By using the trained network, minimisation of the same divergence functional allows for fast, efficient and exact feature selection. Finally, the performance of the algorithms is illustrated on a synthetic dataset.

Original languageEnglish
Title of host publicationIEEE International Conference on Neural Networks - Conference Proceedings
Pages3229-3234
Number of pages6
Volume4
Publication statusPublished - 2004
Event2004 IEEE International Joint Conference on Neural Networks - Proceedings - Budapest, Hungary
Duration: Jul 25 2004Jul 29 2004

Other

Other2004 IEEE International Joint Conference on Neural Networks - Proceedings
CountryHungary
CityBudapest
Period7/25/047/29/04

Fingerprint

Feature extraction
Neural networks

ASJC Scopus subject areas

  • Software

Cite this

Eleuteri, A., Tagliaferri, R., Milano, L., & De Laurentiis, M. (2004). An information geometric approach to survival analysis and feature selection by neural networks. In IEEE International Conference on Neural Networks - Conference Proceedings (Vol. 4, pp. 3229-3234)

An information geometric approach to survival analysis and feature selection by neural networks. / Eleuteri, Antonio; Tagliaferri, Roberta; Milano, Leopoldo; De Laurentiis, Michele.

IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 4 2004. p. 3229-3234.

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

Eleuteri, A, Tagliaferri, R, Milano, L & De Laurentiis, M 2004, An information geometric approach to survival analysis and feature selection by neural networks. in IEEE International Conference on Neural Networks - Conference Proceedings. vol. 4, pp. 3229-3234, 2004 IEEE International Joint Conference on Neural Networks - Proceedings, Budapest, Hungary, 7/25/04.
Eleuteri A, Tagliaferri R, Milano L, De Laurentiis M. An information geometric approach to survival analysis and feature selection by neural networks. In IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 4. 2004. p. 3229-3234
Eleuteri, Antonio ; Tagliaferri, Roberta ; Milano, Leopoldo ; De Laurentiis, Michele. / An information geometric approach to survival analysis and feature selection by neural networks. IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 4 2004. pp. 3229-3234
@inproceedings{7e79ca12ec2e46a982c73ec24ec667b0,
title = "An information geometric approach to survival analysis and feature selection by neural networks",
abstract = "In this paper an information geometric approach to survival analysis is described. It is shown how a neural network can be used to model the probability of failure of a system, and how it can be trained by minimising a suitable divergence functional in a Bayesian framework. By using the trained network, minimisation of the same divergence functional allows for fast, efficient and exact feature selection. Finally, the performance of the algorithms is illustrated on a synthetic dataset.",
author = "Antonio Eleuteri and Roberta Tagliaferri and Leopoldo Milano and {De Laurentiis}, Michele",
year = "2004",
language = "English",
volume = "4",
pages = "3229--3234",
booktitle = "IEEE International Conference on Neural Networks - Conference Proceedings",

}

TY - GEN

T1 - An information geometric approach to survival analysis and feature selection by neural networks

AU - Eleuteri, Antonio

AU - Tagliaferri, Roberta

AU - Milano, Leopoldo

AU - De Laurentiis, Michele

PY - 2004

Y1 - 2004

N2 - In this paper an information geometric approach to survival analysis is described. It is shown how a neural network can be used to model the probability of failure of a system, and how it can be trained by minimising a suitable divergence functional in a Bayesian framework. By using the trained network, minimisation of the same divergence functional allows for fast, efficient and exact feature selection. Finally, the performance of the algorithms is illustrated on a synthetic dataset.

AB - In this paper an information geometric approach to survival analysis is described. It is shown how a neural network can be used to model the probability of failure of a system, and how it can be trained by minimising a suitable divergence functional in a Bayesian framework. By using the trained network, minimisation of the same divergence functional allows for fast, efficient and exact feature selection. Finally, the performance of the algorithms is illustrated on a synthetic dataset.

UR - http://www.scopus.com/inward/record.url?scp=10944241570&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=10944241570&partnerID=8YFLogxK

M3 - Conference contribution

VL - 4

SP - 3229

EP - 3234

BT - IEEE International Conference on Neural Networks - Conference Proceedings

ER -