ML Anthology

Transductive Confidence Machines for Pattern Recognition

Kostas Proedrou, Ilia Nouretdinov, Volodya Vovk, Alex Gammerman
ECML-PKDD 2002 pp. 381-390
doi:10.1007/3-540-36755-1_32 /ecmlpkdd/2002/proedrou2002ecml-transductive/

Abstract

We propose a new algorithm for pattern recognition that outputs some measures of “reliability” for every prediction made, in contrast to the current algorithms that output “bare” predictions only. Our method uses a rule similar to that of nearest neighbours to infer predictions; thus its predictive performance is close to that of nearest neighbours, while the measures of confidence it outputs provide practically useful information for individual predictions.

PDF ECML-PKDD Semantic Scholar

Cite

Text

Proedrou et al. "Transductive Confidence Machines for Pattern Recognition." European Conference on Machine Learning, 2002. doi:10.1007/3-540-36755-1_32

Markdown

[Proedrou et al. "Transductive Confidence Machines for Pattern Recognition." European Conference on Machine Learning, 2002.](https://mlanthology.org/ecmlpkdd/2002/proedrou2002ecml-transductive/) doi:10.1007/3-540-36755-1_32

BibTeX

@inproceedings{proedrou2002ecml-transductive,
  title     = {{Transductive Confidence Machines for Pattern Recognition}},
  author    = {Proedrou, Kostas and Nouretdinov, Ilia and Vovk, Volodya and Gammerman, Alex},
  booktitle = {European Conference on Machine Learning},
  year      = {2002},
  pages     = {381-390},
  doi       = {10.1007/3-540-36755-1_32},
  url       = {https://mlanthology.org/ecmlpkdd/2002/proedrou2002ecml-transductive/}
}