Figure 6
From: L2-norm multiple kernel learning and its application to biomedical data fusion
The effect of θ min in weighted LSSVM MKL and weighted SVM MKL classifier on pregnancy data set. The effect of θ min in LSSVM MKL and SVM MKL classifiers on pregnancy data set. Figure on the left: performance of the regularized LSSVM L∞ MKL with various θ min values. Figure on the right: performance of the regularized SVM L∞ MKL. The black dashed lines represent the performance of the L2 MKL classifiers. The error bars are standard deviations of 20 repetitions.