Minimizing Statistical Bias with Queries
Author(s)
Cohn, David A.
DownloadAIM-1552.ps (278.6Kb)
Additional downloads
Metadata
Show full item recordAbstract
I describe an exploration criterion that attempts to minimize the error of a learner by minimizing its estimated squared bias. I describe experiments with locally-weighted regression on two simple kinematics problems, and observe that this "bias-only" approach outperforms the more common "variance-only" exploration approach, even in the presence of noise.
Date issued
1995-09-01Other identifiers
AIM-1552
Series/Report no.
AIM-1552