Teaching randomized learners with feedback

11 years 4 months ago
Teaching randomized learners with feedback
The present paper introduces a new model for teaching randomized learners. Our new model, though based on the classical teaching dimension model, allows to study the influence of the learner’s memory size and of the presence or absence of feedback. Moreover, in the new model the order in which examples are presented may influence the teaching process. The resulting models are related to Markov decision processes, and characterizations of optimal teachers for memoryless learners with feedback and for learners with infinite memory and feedback are shown. Furthermore, in the new model it is possible to investigate new aspects of teaching like teaching from positive data only or teaching with inconsistent teachers. Characterization theorems for teachability from positive data for both ordinary teachers and inconsistent teachers with and without feedback are provided. Key words: Algorithmic teaching, randomized algorithms, computational complexity
Frank J. Balbach, Thomas Zeugmann
Added 14 May 2011
Updated 14 May 2011
Type Journal
Year 2011
Authors Frank J. Balbach, Thomas Zeugmann
Comments (0)