Performance of the Bayesian online algorithm for the perceptron

Evaldo Araújo de Oliveira, Roberto C. Alamino

Research output: Contribution to journalLetter

Abstract

In this letter, we derive continuum equations for the generalization error of the Bayesian online algorithm (BOnA) for the one-layer perceptron with a spherical covariance matrix using the Rosenblatt potential and show, by numerical calculations, that the asymptotic performance of the algorithm is the same as the one for the optimal algorithm found by means of variational methods with the added advantage that the BOnA does not use any inaccessible information during learning.

Original languageEnglish
Pages (from-to)902-905
Number of pages4
JournalIEEE Transactions on Neural Networks and Learning Systems
Volume18
Issue number3
DOIs
Publication statusPublished - May 2007

Fingerprint

Online Algorithms
Perceptron
Neural networks
Generalization Error
Optimal Algorithm
Variational Methods
Numerical Calculation
Covariance matrix
Continuum
Learning

Keywords

  • Bayesian algorithms
  • online gradient methods
  • pattern classification

Cite this

@article{82d67a10e0d34dc9b6f54a626e5f29d7,
title = "Performance of the Bayesian online algorithm for the perceptron",
abstract = "In this letter, we derive continuum equations for the generalization error of the Bayesian online algorithm (BOnA) for the one-layer perceptron with a spherical covariance matrix using the Rosenblatt potential and show, by numerical calculations, that the asymptotic performance of the algorithm is the same as the one for the optimal algorithm found by means of variational methods with the added advantage that the BOnA does not use any inaccessible information during learning.",
keywords = "Bayesian algorithms, online gradient methods, pattern classification",
author = "{de Oliveira}, {Evaldo Ara{\'u}jo} and Alamino, {Roberto C.}",
year = "2007",
month = "5",
doi = "10.1109/TNN.2007.891189",
language = "English",
volume = "18",
pages = "902--905",
journal = "IEEE Transactions on Neural Networks and Learning Systems",
issn = "1045-9227",
publisher = "IEEE",
number = "3",

}

Performance of the Bayesian online algorithm for the perceptron. / de Oliveira, Evaldo Araújo; Alamino, Roberto C.

In: IEEE Transactions on Neural Networks and Learning Systems, Vol. 18, No. 3, 05.2007, p. 902-905.

Research output: Contribution to journalLetter

TY - JOUR

T1 - Performance of the Bayesian online algorithm for the perceptron

AU - de Oliveira, Evaldo Araújo

AU - Alamino, Roberto C.

PY - 2007/5

Y1 - 2007/5

N2 - In this letter, we derive continuum equations for the generalization error of the Bayesian online algorithm (BOnA) for the one-layer perceptron with a spherical covariance matrix using the Rosenblatt potential and show, by numerical calculations, that the asymptotic performance of the algorithm is the same as the one for the optimal algorithm found by means of variational methods with the added advantage that the BOnA does not use any inaccessible information during learning.

AB - In this letter, we derive continuum equations for the generalization error of the Bayesian online algorithm (BOnA) for the one-layer perceptron with a spherical covariance matrix using the Rosenblatt potential and show, by numerical calculations, that the asymptotic performance of the algorithm is the same as the one for the optimal algorithm found by means of variational methods with the added advantage that the BOnA does not use any inaccessible information during learning.

KW - Bayesian algorithms

KW - online gradient methods

KW - pattern classification

UR - http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=4182376

UR - http://www.scopus.com/inward/record.url?scp=34248663836&partnerID=8YFLogxK

U2 - 10.1109/TNN.2007.891189

DO - 10.1109/TNN.2007.891189

M3 - Letter

VL - 18

SP - 902

EP - 905

JO - IEEE Transactions on Neural Networks and Learning Systems

JF - IEEE Transactions on Neural Networks and Learning Systems

SN - 1045-9227

IS - 3

ER -