Multi-objective optimization and Meta-learning for SVM parameter selection.
Péricles B. C. de MirandaRicardo Bastos Cavalcante PrudêncioAndré Carlos Ponce de Leon Ferreira de CarvalhoCarlos SoaresPublished in: IJCNN (2012)
Keyphrases
- multi objective optimization
- parameter selection
- meta learning
- model selection
- multi objective
- feature selection
- evolutionary algorithm
- support vector machine svm
- support vector
- ls svm
- inductive learning
- machine learning
- support vector machine
- learning tasks
- cross validation
- genetic algorithm
- knn
- svm classifier
- machine learning algorithms
- differential evolution
- decision trees
- hyperparameters
- variable selection
- kernel function
- multi class
- generalization ability
- k nearest neighbor
- particle swarm optimization
- base classifiers
- kernel methods
- training set
- metamodel
- feature vectors
- radial basis function
- objective function
- training data