Synopsis
A regularized generale discriminant function for binominal labels and numerical attributes.
Description
This is a regularized discriminant analysis (RDA) which is a generalization of the LDA or QDA. Both algorithms are special cases of this algorithm, using parameter alpha = 1 respectively alpha = 0.
Input
- training set: expects: ExampleSet
Output
- model:
- exampleSet:
Parameters
- alpha: This is the strength of regularization. 1: Only global covariance is used, 0: Only per class covariance is used.