Linear separability analysis for stacked generalization architecture

Stacked Generalization algorithm aims to increase the individual classification performances of the classifiers by combining the information obtained from various classifiers in a multilayer architecture by either linear or nonlinear techniques. Performance of the algorithm varies depending on the application domains and the space analyses that affect the classification performances could not be applied successfully. In the present work, linear and nonlinear transformations are investigated within and between each layer, and the linear separability property of the architecture is examined. In the conclusion of the analyses, it is observed that the data space can be separated linearly.