Low density separation as a stopping criterion for active learning SVM.
Chunjiang FuYupu YangPublished in: Intell. Data Anal. (2015)
Keyphrases
- low density
- stopping criterion
- active learning
- high density
- support vector machine svm
- support vector
- training set
- convergence rate
- support vector machine
- sample selection
- machine learning
- cost function
- knn
- svm classifier
- cost sensitive
- merging algorithm
- multi class
- training data
- semi supervised
- training examples
- feature selection
- active learning framework
- learning process
- labeled data
- feature vectors
- clustering algorithm
- active contours
- databases
- region merging
- computer vision
- learning algorithm