Efficient Pattern Recognition Using a New Transformation Distance

  title={Efficient Pattern Recognition Using a New Transformation Distance},
  author={Patrice Y. Simard and Yann LeCun and John S. Denker},
Memory-based classification algorithms such as radial basis functions or K-nearest neighbors typically rely on simple distances (Euclidean, dot product ... ), which are not particularly meaningful on pattern vectors. More complex, better suited distance measures are often expensive and rather ad-hoc (elastic matching, deformable templates). We propose a new distance measure which (a) can be made locally invariant to any set of transformations of the input and (b) can be computed efficiently. We… CONTINUE READING
Highly Influential
This paper has highly influenced 31 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 633 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 318 extracted citations

634 Citations

Citations per Year
Semantic Scholar estimates that this publication has 634 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-6 of 6 references

Self-organization and Associative Memory

  • T. Kohonen
  • In Springer Sedes in Information Sciences,
  • 1984
Highly Influential
3 Excerpts

An Efficient Met.hod for Learning Invariances in Adaptive classifiers

  • P. Y. Simard, Y. LeCun, J. Denker, B. Victorri
  • In International Conference on Pattern…
  • 1992
3 Excerpts

Studies in the Robustness of Multidimensiona . l Scaling : Procrust . es Statistices . 1

  • R. Sibson
  • . R . Statist . Soc .
  • 1978
1 Excerpt

Studies in the Robustness of Multidimensiona.l Scaling: Procrust.es Statistices

  • R. Sibson
  • 1. R. Statist. Soc.,
  • 1978
1 Excerpt

Similar Papers

Loading similar papers…