Title

Learning From a Consistently Ignorant Teacher

Authors

Michael Frazier, Washington University in St Louis
Sally Goldman, Washington University in St Louis
Nina Mishra, Washington University in St Louis
Leonard Pitt, Washington University in St Louis

Document Type

Technical Report

Department

Computer Science and Engineering

Publication Date

1994-01-01

Filename

WUCS-94-2.PDF

DOI:

10.7936/K7TD9VJR

Technical Report Number

WUCS-94-2

Abstract

One view of computational learning theory is that of a learner acquiring the knowledge of a teacher. We introduce a formal model of learning capturing the idea that teachers may have gaps in their knowledge. The goal of the learner is still to acquire the knowledge of the teacher, but now the learner must also identify the gaps. This is the notion of learning from a consistently ignorant teacher. We consider the impact of knowledge gaps on learning, for example, monoton DNF and d-dimensional boxes, and show that leraning is still possible. Negatively, we show that knowledge gaps make learning conjunctions of Horn clauses as hard as learning DNF. We also present general results describing when known learning algorithms can be used to obtain learning algorithms using a consistently ignorant teacher.

Comments

Permanent URL: http://dx.doi.org/10.7936/K7TD9VJR

Recommended Citation

Frazier, Michael; Goldman, Sally; Mishra, Nina; and Pitt, Leonard, "Learning From a Consistently Ignorant Teacher" Report Number: WUCS-94-2 (1994). All Computer Science and Engineering Research.
https://openscholarship.wustl.edu/cse_research/341