Please use this identifier to cite or link to this item:
|Title:||Learning in the presence of inaccurate information||Authors:||Fulk, M.
|Issue Date:||15-Jul-1996||Citation:||Fulk, M.,Jain, S. (1996-07-15). Learning in the presence of inaccurate information. Theoretical Computer Science 161 (1-2) : 235-261. ScholarBank@NUS Repository.||Abstract:||The present paper considers the effects of introducing inaccuracies in a learner's environment in Gold's learning model of identification in the limit. Three kinds of inaccuracies are considered: presence of spurious data is modeled as learning from a noisy environment, missing data is modeled as learning from incomplete environment, and the presence of a mixture of both spurious and missing data is modeled as learning from imperfect environment. Two learning domains are considered, namely, identification of programs from graphs of computable functions and identification of grammars from positive data about recursively enumerable languages. Many hierarchies and tradeoffs resulting from the interplay between the number of errors allowed in the final hypotheses, the number of inaccuracies in the data, the types of inaccuracies, and the type of success criteria are derived. An interesting result is that in the context of function learning, incomplete data is strictly worse for learning than noisy data.||Source Title:||Theoretical Computer Science||URI:||http://scholarbank.nus.edu.sg/handle/10635/99326||ISSN:||03043975|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Sep 19, 2020
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.