Optimal online learning: A Bayesian approach

Sara A. Solla, Ole Winther

Research output: Contribution to journalConference articlepeer-review

3 Scopus citations


A recently proposed Bayesian approach to online learning is applied to learning a rule defined as a noisy single layer perceptron. In the Bayesian online approach, the exact posterior distribution is approximated by a simple parametric posterior that is updated online as new examples are incorporated to the dataset. In the case of binary weights, the approximate posterior is chosen to be a biased binary distribution. The resulting online algorithm is shown to outperform several other online approaches to this problem.

Original languageEnglish (US)
Pages (from-to)94-97
Number of pages4
JournalComputer Physics Communications
StatePublished - Sep 1999
EventProceedings of the 1998 Europhysics Conference on Computational Physics (CCP 1998) - Granada, Spain
Duration: Sep 2 1998Sep 5 1998

ASJC Scopus subject areas

  • Hardware and Architecture
  • Physics and Astronomy(all)


Dive into the research topics of 'Optimal online learning: A Bayesian approach'. Together they form a unique fingerprint.

Cite this