Feature/Model Selection by the Linear Programming SVM Combined with State-of-Art Classifiers: What Can We Learn About the Data.
Erinija PranckevicieneRay L. SomorjaiMuoi N. TranPublished in: IJCNN (2007)
Keyphrases
- model selection
- data sets
- linear programming
- support vector
- feature selection
- training data
- cross validation
- training set
- selection criterion
- hyperparameters
- maximum likelihood
- data points
- feature space
- decision trees
- missing data
- sample size
- svm classifier
- support vectors
- bayesian methods
- meta learning
- feature vectors
- generalization ability
- feature subset
- prior knowledge
- mutual information
- parameter estimation
- mixture model
- knn