Operating modern digital environments, as computer software and digital instruments require users to master a large variety of cognitive, motor, sociological, and emotional skills...
In this paper we introduce and investigate a mathematically rigorous theory of learning curves that is based on ideas from statistical mechanics. The advantage of our theory over ...
David Haussler, H. Sebastian Seung, Michael J. Kea...
This paper describes an application of active learning methods to the classification of phone strings recognized using unsupervised phonotactic models. The only training data req...
We present a discriminative method for learning selectional preferences from unlabeled text. Positive examples are taken from observed predicate-argument pairs, while negatives ar...
Given a model family and a set of unlabeled examples, one could either label specific examples or state general constraints--both provide information about the desired model. In g...