A hybrid isotonic separation training algorithm with correlation-based isotonic feature selection for binary classification.
B. MalarR. NadarajanJ. Gowri ThangamPublished in: Knowl. Inf. Syst. (2019)
Keyphrases
- training algorithm
- binary classification
- support vector machine
- feature selection
- multi class
- support vector
- back propagation
- neural network
- cost sensitive
- training process
- rbf neural network
- generalization error
- class imbalance
- multi label
- text categorization
- feature space
- feature vectors
- radial basis function
- kernel methods
- support vector machine svm
- k nearest neighbor
- text classification
- kernel function
- learning problems
- classification accuracy
- training set
- feature extraction
- machine learning
- feature set
- knn
- training data
- benchmark datasets
- learning experience
- optimization method
- pattern recognition
- hidden layer