On the Teachability of Randomized Learners

Authors Frank J. Balbach, Thomas Zeugmann



PDF
Thumbnail PDF

File

DagSemProc.06111.13.pdf
  • Filesize: 268 kB
  • 21 pages

Document Identifiers

Author Details

Frank J. Balbach
Thomas Zeugmann

Cite AsGet BibTex

Frank J. Balbach and Thomas Zeugmann. On the Teachability of Randomized Learners. In Complexity of Boolean Functions. Dagstuhl Seminar Proceedings, Volume 6111, pp. 1-20, Schloss Dagstuhl – Leibniz-Zentrum für Informatik (2006)
https://doi.org/10.4230/DagSemProc.06111.13

Abstract

The present paper introduces a new model for teaching {em randomized learners}. Our new model, though based on the classical teaching dimension model, allows to study the influence of various parameters such as the learner's memory size, its ability to provide or to not provide feedback, and the influence of the order in which examples are presented. Furthermore, within the new model it is possible to investigate new aspects of teaching like teaching from positive data only or teaching with inconsistent teachers. Furthermore, we provide characterization theorems for teachability from positive data for both ordinary teachers and inconsistent teachers with and without feedback.
Keywords
  • Algorithmic Teaching
  • Complexity of teaching

Metrics

  • Access Statistics
  • Total Accesses (updated on a weekly basis)
    0
    PDF Downloads
Questions / Remarks / Feedback
X

Feedback for Dagstuhl Publishing


Thanks for your feedback!

Feedback submitted

Could not send message

Please try again later or send an E-mail