Optimal Training Data Selection in Active Learning for Discrimination and Classification.
Xiaojian XuCharlie ShayPublished in: ICCCS (2020)
Keyphrases
- active learning
- training data
- classification accuracy
- training set
- annotation effort
- sample selection
- decision trees
- supervised learning
- feature selection
- classification models
- class labels
- training examples
- machine learning
- training process
- training samples
- support vector machine
- classification method
- pattern recognition
- random selection
- selective sampling
- classification algorithm
- support vector
- labeling effort
- feature subset
- learning algorithm
- feature extraction
- benchmark datasets
- neural network
- labeled data
- unseen data
- binary decision tree
- dynamic programming
- selection strategies
- imbalanced data classification
- naive bayes
- feature space
- optimal solution
- incremental learning
- test data
- generalization error
- cross validation
- class imbalance
- classification trees
- model selection
- text classification
- image classification
- prior knowledge
- learning process
- sufficient training data
- feature vectors