Deciding on the unimodality of a dataset is an important problem in data analysis and statistical modeling. It allows to obtain knowledge about structure dataset, ie. whether points have been generated by probability distribution with single or more than one peaks. Such very useful for several problems, such as deciding number clusters determining unimodal projections. We propose technique call...

Although kernel measures of independence have been widely applied in machine learning (notably in kernel ICA), there is as yet no method to determine whether they have detected statistically significant dependence. We provide a novel test of the independence hypothesis for one particular kernel independence measure, the Hilbert-Schmidt independence criterion (HSIC). The resulting test costs O(m...

Assessing whether two models are statistically significantly different from each other is a very important step in research, although it has unfortunately not received enough attention in the field of person authentication. Several performance measures are often used to compare models, such as half total error rates (HTERs) and equal error rates (EERs), but most being aggregates of two measures...

The correction is in two parts. See [3] for more information on the correction. 1. The LPEadj method discontinues the LPE practice of setting all variances below the maximum variance in the ordered distribution of variances to the maximum variance. In certain cases this practice can set many variances to the maximum and lower the performance of this algorithm. If the assumption that there are o...