ML Anthology

Learning with Queries but Incomplete Information (Extended Abstract)

Robert H. Sloan, György Turán
COLT 1994 pp. 237-245
doi:10.1145/180139.181128 /colt/1994/sloan1994colt-learning/

Abstract

We investigate learning with membership and equivalence queries assuming that the information provided to the learner is incomplete. By incomplete we mean that some of the membership queries may be answered by “I don't know.” This model is a worst-case version of the incomplete membership query model of Angluin and Slonim. It attempts to model practical learning situations, including an experiment of Lang and Baum that we describe, where the teacher may be unable to answer reliably some queries that are critical for the learning algorithm.

PDF COLT Semantic Scholar

Cite

Text

Sloan and Turán. "Learning with Queries but Incomplete Information (Extended Abstract)." Annual Conference on Computational Learning Theory, 1994. doi:10.1145/180139.181128

Markdown

[Sloan and Turán. "Learning with Queries but Incomplete Information (Extended Abstract)." Annual Conference on Computational Learning Theory, 1994.](https://mlanthology.org/colt/1994/sloan1994colt-learning/) doi:10.1145/180139.181128

BibTeX

@inproceedings{sloan1994colt-learning,
  title     = {{Learning with Queries but Incomplete Information (Extended Abstract)}},
  author    = {Sloan, Robert H. and Turán, György},
  booktitle = {Annual Conference on Computational Learning Theory},
  year      = {1994},
  pages     = {237-245},
  doi       = {10.1145/180139.181128},
  url       = {https://mlanthology.org/colt/1994/sloan1994colt-learning/}
}