Importance Sampling for Objetive Funtion Estimations in Neural Detector Traing Driven by Genetic Algorithms

Vicen Bueno, Raul and Jarabo Amores, M. Pilar and Rosa Zurera, Manuel and Sanz Gonzalez, Jose Luis and Maldonado Bascon, Saturnino (2010). Importance Sampling for Objetive Funtion Estimations in Neural Detector Traing Driven by Genetic Algorithms. "Neural Processing Letters", v. 32 (n. 3); pp. 249-268. ISSN 1370-4621. https://doi.org/10.1007/s11063-010-9155-8.

Description

Title: Importance Sampling for Objetive Funtion Estimations in Neural Detector Traing Driven by Genetic Algorithms
Author/s:
  • Vicen Bueno, Raul
  • Jarabo Amores, M. Pilar
  • Rosa Zurera, Manuel
  • Sanz Gonzalez, Jose Luis
  • Maldonado Bascon, Saturnino
Item Type: Article
Título de Revista/Publicación: Neural Processing Letters
Date: December 2010
ISSN: 1370-4621
Volume: 32
Subjects:
Freetext Keywords: Genetic algorithms - Neural networks - Monte Carlo - Importance sampling - Mean-Square error - Cross Entropy error - Misclassification error
Faculty: E.T.S.I. Telecomunicación (UPM)
Department: Señales, Sistemas y Radiocomunicaciones
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (889kB) | Preview

Abstract

To train Neural Networks (NNs) in a supervised way, estimations of an objective function must be carried out. The value of this function decreases as the training progresses and so, the number of test observations necessary for an accurate estimation has to be increased. Consequently, the training computational cost is unaffordable for very low objective function value estimations, and the use of Importance Sampling (IS) techniques becomes convenient. The study of three different objective functions is considered, which implies the proposal of estimators of the objective function using IS techniques: the Mean-Square error, the Cross Entropy error and the Misclassification error criteria. The values of these functions are estimated by IS techniques, and the results are used to train NNs by the application of Genetic Algorithms. Results for a binary detection in Gaussian noise are provided. These results show the evolution of the parameters during the training and the performances of the proposed detectors in terms of error probability and Receiver Operating Characteristics curves. At the end of the study, the obtained results justify the convenience of using IS in the training.

More information

Item ID: 9556
DC Identifier: http://oa.upm.es/9556/
OAI Identifier: oai:oa.upm.es:9556
DOI: 10.1007/s11063-010-9155-8
Official URL: http://www.springerlink.com/content/b2704072q0368q87/
Deposited by: Memoria Investigacion
Deposited on: 07 Nov 2011 08:59
Last Modified: 20 Apr 2016 17:55
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM