A lagrangian-based approach for universum twin bounded support vector machine with its applications.
Hossein MoosaeiMilan HladíkPublished in: Ann. Math. Artif. Intell. (2023)
Keyphrases
- support vector machine
- binary classification
- maximum margin
- unbalanced data
- semi supervised learning
- multi class
- support vector
- training data
- machine learning
- kernel methods
- hyperplane
- semi supervised
- semi definite programming
- generalization ability
- svm classifier
- feature vectors
- support vector machine svm
- learning problems
- feature selection
- kernel function
- learning algorithm
- support vectors
- training set
- svm classification
- multi label
- structured output
- pattern classification
- decision boundary
- labeled samples
- misclassification costs
- binary classifiers
- target domain
- active learning
- ensemble methods
- cost sensitive