3624 search results - page 186 / 725 » Learning to learn: From smart machines to intelligent machin... |
136
click to vote
IFSA
2007
Springer
16 years 22 days ago
2007
Springer
Typically the response of a multilayered perceptron (MLP) network on points which are far away from the boundary of its training data is not very reliable. When test data points ar...
155
click to vote
ALT
2006
Springer
16 years 3 months ago
2006
Springer
A model for learning in the limit is defined where a (so-called iterative) learner gets all positive examples from the target language, tests every new conjecture with a teacher ...
151
click to vote
COLT
2005
Springer
16 years 3 days ago
2005
Springer
Abstract. There has been growing interest in practice in using unlabeled data together with labeled data in machine learning, and a number of different approaches have been develo...
199
click to vote
JMLR
2006
15 years 6 months ago
2006
We propose a family of learning algorithms based on a new form of regularization that allows us to exploit the geometry of the marginal distribution. We focus on a semi-supervised...
159
click to vote
ALT
2009
Springer
16 years 3 months ago
2009
Springer
Abstract. A variant of iterative learning in the limit (cf. [LZ96]) is studied when a learner gets negative examples refuting conjectures containing data in excess of the target la...