1553 search results - page 1 / 311 » Learning from Multiple Sources of Inaccurate Data |
AII
1992
13 years 9 months ago
1992
Most theoretical models of inductive inference make the idealized assumption that the data available to a learner is from a single and accurate source. The subject of inaccuracies ...
CAISE
2010
Springer
13 years 6 months ago
2010
Springer
There is a large amount of data that is published on the Web and several techniques have been developed to extract and integrate data from Web sources. However, Web data are inhere...
ICRA
2009
IEEE
13 years 11 months ago
2009
IEEE
— Traditional approaches to programming robots are generally inaccessible to non-robotics-experts. A promising exception is the Learning from Demonstration paradigm. Here a polic...
NIPS
2007
13 years 6 months ago
2007
Empirical risk minimization offers well-known learning guarantees when training and test data come from the same domain. In the real world, though, we often wish to adapt a classi...
COLT
1989
Springer
13 years 9 months ago
1989
Springer
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 inaccu...