Estimation of Individual Prediction Reliability Using Sensitivity Analysis of Regression Models

The paper is the extended abstract of dissertation which is concerned with the estimation of reliability for the individual predictions of regression models (in contrast to estimating the accuracy of the whole model) and with the use of sensitivity analysis in that area. The dissertation studies the ways of optimal reliability estimate selection among 9 studied reliability estimates and evaluates the methodology on large number of standard benchmark domain as well as on real domains. Povzetek: Članek povzema doktorsko disertacijo, ki se ukvarja z ocenjevanjem zanesljivosti posameznih regresijskih napovedi v strojnem učenju