TY - JOUR
T1 - On learning from queries and counterexamples in the presence of noise
AU - Sakakibara, Yasubumi
PY - 1991/3/14
Y1 - 1991/3/14
N2 - Recently Angluin and Laird have introduced the classification noise process in the Valiant learnability model and proposed an interesting problem to explore the effect of noise in a situation that calls for queries as well as random sampling. In this paper, we present a general method to modify a polynomial-time learning algorithm from a sampling oracle and membership queries to compensate for random errors in the sampling and query responses.
AB - Recently Angluin and Laird have introduced the classification noise process in the Valiant learnability model and proposed an interesting problem to explore the effect of noise in a situation that calls for queries as well as random sampling. In this paper, we present a general method to modify a polynomial-time learning algorithm from a sampling oracle and membership queries to compensate for random errors in the sampling and query responses.
KW - Concept learning
KW - analysis of algorithms
KW - formal languages
KW - noise
KW - queries
KW - random sampling
UR - http://www.scopus.com/inward/record.url?scp=0026119624&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0026119624&partnerID=8YFLogxK
U2 - 10.1016/0020-0190(91)90220-C
DO - 10.1016/0020-0190(91)90220-C
M3 - Article
AN - SCOPUS:0026119624
SN - 0020-0190
VL - 37
SP - 279
EP - 284
JO - Information Processing Letters
JF - Information Processing Letters
IS - 5
ER -