Online Learning with (Multiple) Kernels: A Review

Tom Diethe*, Mark Girolami

*Corresponding author for this work

Research output: Contribution to journalReview article (Academic Journal)peer-review

25 Citations (Scopus)

Abstract

This review examines kernel methods for online learning, in particular, multiclass classification. We examine margin-based approaches, stemming from Rosenblatt's original perceptron algorithm, as well as nonparametric probabilistic approaches that are based on the popular gaussian process framework. We also examine approaches to online learning that use combinations of kernels online multiple kernel learning. We present empirical validation of a wide range of methods on a protein fold recognition data set, where different biological feature types are available, and two object recognition data sets, Caltech101 and Caltech256, where multiple feature spaces are available in terms of different image feature extraction methods.

Original languageEnglish
Pages (from-to)567-625
Number of pages59
JournalNeural Computation
Volume25
Issue number3
Publication statusPublished - Mar 2013

Keywords

  • LARGE MARGIN CLASSIFICATION
  • PROTEIN FOLD RECOGNITION
  • PERCEPTRON ALGORITHM
  • TRACKING
  • PREDICTION
  • MODELS
  • EXPERT
  • BUDGET
  • BRAIN

Cite this