An adaptive cost-sensitive learning approach in neural networks to minimize local training-test class distributions mismatch.
Ohad VolkGonen SingerPublished in: Intell. Syst. Appl. (2024)
Keyphrases
- cost sensitive learning
- class distribution
- misclassification costs
- cost sensitive
- training set
- neural network
- class imbalance
- test set
- training examples
- training samples
- imbalanced datasets
- test data
- rule extraction
- training data
- classification error
- unlabeled data
- test cases
- probability estimation
- class labels
- missing values
- decision trees
- data sets
- supervised learning
- classification accuracy
- naive bayes
- base classifiers
- support vector machine
- high dimensional
- small number
- classification algorithm
- error rate
- face recognition
- multi class
- minority class
- labeled data