## Files in this item

FilesDescriptionFormat

application/pdf

9812710.pdf (6MB)
(no description provided)PDF

## Description

 Title: Learning From a Monotonous, Ignorant Teacher Author(s): Mishra, Nina Doctoral Committee Chair(s): Pitt, Leonard Department / Program: Computer Science Discipline: Computer Science Degree Granting Institution: University of Illinois at Urbana-Champaign Degree: Ph.D. Genre: Dissertation Subject(s): Artificial Intelligence Abstract: The third learning setting combines the first and second in that we both give our computer preclassified examples and allow it to pose membership queries. The unknown function f may now classify examples in one of three possible ways: "+", "$-$" or "?". We prove general results for when it is possible for a computer to learn to be ignorant in this three-valued setting (+, $-$, ?) that utilizes results from the two-valued (+, $-$) setting. The three-valued setting we consider differs from the standard three-valued setting in that the set of possible functions that f could be, together with the set of "+", "$-$" examples determine which examples can be classified "?". Issue Date: 1997 Type: Text Language: English Description: 108 p.Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 1997. URI: http://hdl.handle.net/2142/81903 Other Identifier(s): (MiAaPQ)AAI9812710 Date Available in IDEALS: 2015-09-25 Date Deposited: 1997
﻿