A Bayesian approach to on-line learning

Abstract

Online learning is discussed from the viewpoint of Bayesian statistical inference. By replacing the true posterior distribution with a simpler parametric distribution, one can define an online algorithm by a repetition of two steps: An update of the approximate posterior, when a new example arrives, and an optimal projection into the parametric family. Choosing this family to be Gaussian, we show that the algorithm achieves asymptotic efficiency. An application to learning in single layer neural networks is given.

Publication DOI: https://doi.org/10.2277/0521652634
Divisions: College of Engineering & Physical Sciences > Systems analytics research institute (SARI)
Additional Information: Copyright of Cambridge University Press Available on Google Books
Uncontrolled Keywords: Online learning,Bayesian statistical inference,asymptotic efficiency,neural networks
ISBN: 0262194163
Last Modified: 06 Dec 2024 08:34
Date Deposited: 05 Aug 2009 13:32
Full Text Link:
Related URLs: http://www.camb ... isbn=0521652634 (Publisher URL)
PURE Output Type: Chapter
Published Date: 1999-01
Authors: Opper, Manfred
Winther, Ole

Download

[img]

Version: Accepted Version


Export / Share Citation


Statistics

Additional statistics for this record