Skip to main content
Figure 2 | BMC Bioinformatics

Figure 2

From: Prediction using step-wise L1, L2 regularization and feature selection for small data sets with large number of features

Figure 2

Overview of selected features. Feature selection with L1 regularization with increasing λ1 values (from top to bottom) for CoEPrA regression task I. Left vertical axis: λ1 Right vertical axis: number of remaining features after a cycle of L1 regularization with the corresponding λ1 value. Horizontal axis displays the feature index. The initial number of features is 6219. The colors, varying from black to yellow, exhibit how often specific features reappear in the selection procedure after they disappeared in the selection round before. For instance yellow marks features that reappeared seven times for the eight different λ1 values considered.

Back to article page