Training Invariant Support Vector Machines

  • Authors:
  • Dennis Decoste;Bernhard Schö/lkopf

  • Affiliations:
  • Jet Propulsion Laboratory, MS 126-347, 4800 Oak Grove Drive, Pasadena, CA 91109, USA&semi/ California Institute of Technology. decoste@aig.jpl.nasa.gov;Max-Planck-Institut fuer biologische Kybernetik, Spemannstr. 38, 72076 Tü/bingen, Germany. bs@conclu.de

  • Venue:
  • Machine Learning
  • Year:
  • 2002

Quantified Score

Hi-index 0.01

Visualization

Abstract

Practical experience has shown that in order to obtain the best possible performance, prior knowledge about invariances of a classification problem at hand ought to be incorporated into the training procedure. We describe and review all known methods for doing so in support vector machines, provide experimental results, and discuss their respective merits. One of the significant new results reported in this work is our recent achievement of the lowest reported test error on the well-known MNIST digit recognition benchmark task, with SVM training times that are also significantly faster than previous SVM methods.