On the Sample Complexity of PAC-learning using Random and Chosen Examples
Name
MIT-LCS-TR-535.pdf
Size
1.48 MB
Format
Adobe PDF
Checksum (MD5)
71f0e2d0649839e6ba8f44529a4b090d
Author(s)
Eisenberg, Bronwyn Bonnie
Advisor(s)
Rivest, Ronald L.
Date Issued
March 1992
Series/Report no.
MIT-LCS-TR-535
Abstract
Two protocols used for learning under the pac-learning model introduced by Valiant are learning from random examples and learning from memberships queries. Membership queries have been used to efficiently and exactly learn a concept class C that is too difficult to pac-learn using random examples.
Persistent DSpace Link