« Projekte
Sie verwenden einen sehr veralteten Browser und können Funktionen dieser Seite nur sehr eingeschränkt nutzen. Bitte aktualisieren Sie Ihren Browser. http://www.browser-update.org/de/update.html
On the application of deep learning in change point analysis
Projektbearbeiter:
M.Sc. Sajad Safarveisi
Finanzierung:
Land (Sachsen-Anhalt) ;
Deep learning based on multilayer neural networks have recently become the state-of-the-art method in machine learning for classification. They may be used for important economic and industrial applications (e.g. credit scoring, monitoring of critical production processes or safety of computer networks). The applications of those methods heavily depend on homogeneity of the data over time. Therefore, developing methods for checking these assumptions are important, but do not yet exist for such complex networks. The goal of this project is to develop tests for the presence of changes in time for multilayer neural networks based on previous work on single-layer networks (Kirch and Tadjuidje, 2012, 2014) and on parameter estimation for multilayer networks (Bauer and Kohler, 2017).
Kontakt

weitere Projekte

Die Daten werden geladen ...