An Adaptive Pre-filtering Technique for Error-Reduction Sampling in Active Learning.
Michael DavySaturnino LuzPublished in: ICDM Workshops (2008)
Keyphrases
- error reduction
- pre filtering
- active learning
- random sampling
- semi supervised
- class imbalance
- classification error
- iterative learning
- labeled data
- classification accuracy
- training set
- feature selection
- training examples
- generalization error
- significant improvement
- supervised learning
- learning algorithm
- machine learning
- hyperparameters
- data sets
- learning process
- prior information
- sample size
- unlabeled data
- learning environment
- semi supervised learning
- em algorithm