Accurately predicting the cardinality of intermediate plan operations is an essential part of any modern relational query optimizer. The accuracy of said estimates has a strong and direct impact on the quality of the generated plans, and incorrect estimates can have a negative impact on query performance. One of the biggest challenges in this field is to predict the result size of join operatio...

We propose a novel approach to online estimation of probability density functions, which is based on kernel density estimation (KDE). The method maintains and updates a non-parametric model of the observed data, from which the KDE can be calculated. We propose an online bandwidth estimation approach and a compression/revitalization scheme which maintains the KDE’s complexity low. We compare the...

We have used cloned mouse and human DNA probes to identify regions of conserved homology between the human and murine DNA segments, (termed kappa deleting element (kde) and recombining segment (RS) respectively) which are frequently recombined in lambda-producing B cells. Heteroduplex analysis indicated extensive homology in the region immediately downstream of the recombination site of both se...

Studies examined infants' perceptions of 3-dimensional form, using a kinetic depth effect (KDE) display and displays containing subsets of the motion present in the KDE display. One subset consisted of "between-contour" motion, and the second consisted of "within-contour" motion. Research with adults has suggested that only between-contour motion leads to a compelling depth percept. In Experime...

We focus on solving the problem of learning an optimal smoothing kernel for the unsupervised learning problem of kernel density estimation(KDE) by using hyperkernels. The optimal kernel is the one which minimizes the regularized negative leave-one-out-log likelihood score of the train set. We demonstrate that ”fixed bandwidth” and ”variable bandwidth” KDE are special cases of our algorithm.