<> "The repository administrator has not yet configured an RDF license."^^ . <> . . "On the application of\r\nmachine learning approaches in astronomy:\r\nExploring novel representations of\r\nhigh-dimensional and complex astronomical data"^^ . "The goal of the presented work is the application of data-driven methods on complex and high-\r\ndimensional astronomical databases. The focus of the work is the exploration of novel data\r\nrepresentations in order to enable the use of statistical learning approaches in the analysis of\r\ndata. With the help of diverse science cases, the advantages of the introduced approaches for\r\nclassication, visualization and regression tasks are shown by applying the developed methodology\r\nto astronomical data.\r\nIn the first part, an alternative approach for estimating redshifts of spectra by using the\r\nknowledge about the redshifts provided by the SDSS pipeline is presented. A novel data repre-\r\nsentation is employed which contains only information relevant for estimating the redshift and\r\nthe detection of multiple redshift systems. Subsequently, a novel data representation for regu-\r\nlarly sampled light curves based on recurrent networks is presented. This allows an explorative\r\ninvestigation of huge databases with unlabeled data. Finally, a new way of representing the static\r\npart of irregularly sampled light curves by a mixture of Gaussians is discussed. This represen-\r\ntation is more general than the extraction of features, as it allows the inclusion of photometric\r\nuncertainties and avoids the introduction of observational biases.\r\n"^^ . "2015" . . . . . . . "Sven Dennis"^^ . "Kügler"^^ . "Sven Dennis Kügler"^^ . . . . . . "On the application of\r\nmachine learning approaches in astronomy:\r\nExploring novel representations of\r\nhigh-dimensional and complex astronomical data (PDF)"^^ . . . "thesis.pdf"^^ . . . "On the application of\r\nmachine learning approaches in astronomy:\r\nExploring novel representations of\r\nhigh-dimensional and complex astronomical data (Other)"^^ . . . . . . "indexcodes.txt"^^ . . . "On the application of\r\nmachine learning approaches in astronomy:\r\nExploring novel representations of\r\nhigh-dimensional and complex astronomical data (Other)"^^ . . . . . . "lightbox.jpg"^^ . . . "On the application of\r\nmachine learning approaches in astronomy:\r\nExploring novel representations of\r\nhigh-dimensional and complex astronomical data (Other)"^^ . . . . . . "preview.jpg"^^ . . . "On the application of\r\nmachine learning approaches in astronomy:\r\nExploring novel representations of\r\nhigh-dimensional and complex astronomical data (Other)"^^ . . . . . . "medium.jpg"^^ . . . "On the application of\r\nmachine learning approaches in astronomy:\r\nExploring novel representations of\r\nhigh-dimensional and complex astronomical data (Other)"^^ . . . . . . "small.jpg"^^ . . "HTML Summary of #19927 \n\nOn the application of \nmachine learning approaches in astronomy: \nExploring novel representations of \nhigh-dimensional and complex astronomical data\n\n" . "text/html" . . . "004 Informatik"@de . "004 Data processing Computer science"@en . . . "520 Astronomie"@de . "520 Astronomy and allied sciences"@en . .