Corrigendum to Types of Noise in Data for Concept Learning

Abstract

The algorithm for pac learning k-DNF or k-CNF in the presence of malicious attribute noise in polynomial time claimed by Sloan [Slo88] does not work. It is currently open whether such an algorithm exists.

Cite

Text

Sloan. "Corrigendum to Types of Noise in Data for Concept Learning." Annual Conference on Computational Learning Theory, 1992. doi:10.1145/130385.130433

Markdown

[Sloan. "Corrigendum to Types of Noise in Data for Concept Learning." Annual Conference on Computational Learning Theory, 1992.](https://mlanthology.org/colt/1992/sloan1992colt-corrigendum/) doi:10.1145/130385.130433

BibTeX

@inproceedings{sloan1992colt-corrigendum,
  title     = {{Corrigendum to Types of Noise in Data for Concept Learning}},
  author    = {Sloan, Robert H.},
  booktitle = {Annual Conference on Computational Learning Theory},
  year      = {1992},
  pages     = {450},
  doi       = {10.1145/130385.130433},
  url       = {https://mlanthology.org/colt/1992/sloan1992colt-corrigendum/}
}