Geodesic distances in the maximum likelihood estimator of intrinsic dimensionality
Rasa Karbauskaitė, Gintautas Dzemyda, Edmundas Mazėtis · Nonlinear Analysis Modelling and Control · 2011
While analyzing multidimensional data, we often have to reduce their dimensionality so that to preserve as much information on the analyzed data set as possible. To this end, it is reasonable to find out the intrinsic dimensionality of the data. In this paper, two techniques for the intrinsic dimensionality are analyzed and compared, i.e., the maximum likelihood estimator (MLE) and ISOMAP method. We also propose the way how to get good estimates of the intrinsic dimensionality by the MLE method.