165 search results - page 31 / 33 » Teaching Randomized Learners |
NIPS
2003
13 years 9 months ago
2003
In the problem of probability forecasting the learner’s goal is to output, given a training set and a new object, a suitable probability measure on the possible values of the ne...
AAAI
2000
13 years 9 months ago
2000
Selective sampling, a form of active learning, reduces the cost of labeling training data by asking only for the labels of the most informative unlabeled examples. We introduce a ...
TCS
2008
13 years 7 months ago
2008
Studying the learnability of classes of recursive functions has attracted considerable interest for at least four decades. Starting with Gold's (1967) model of learning in th...
IJON
2010
13 years 6 months ago
2010
An active learner usually assumes there are some labeled data available based on which a moderate classifier is learned and then examines unlabeled data to manually label the mos...
AAAI
2011
12 years 8 months ago
2011
Recently, a number of researchers have proposed spectral algorithms for learning models of dynamical systems—for example, Hidden Markov Models (HMMs), Partially Observable Marko...