Using test plans for bayesian modeling

Beitrag bei einer Tagung

Details zur Publikation

Autor(en): Deventer R, Denzler J, Niemann H, Kreis O
Herausgeber: Perner P.; Rosenfeld A.
Verlag: Springer
Verlagsort: Berlin
Jahr der Veröffentlichung: 2003
Band: 2734
Tagungsband: Machine Learning and Data Mining in Pattern Recognition
Seitenbereich: 307-316
Sprache: Englisch


When modeling technical processes, the training data regularly come from test plans, to reduce the number of experiments and to save time and costs. On the other hand, this leads to unobserved combinations of the input variables. In this article it is shown, that these unobserved configurations might lead to un-trainable parameters. Afterwards a possible design criterion is introduced, which avoids this drawback. Our approach is tested to model a welding process. The results show, that hybrid Bayesian networks are able to deal with yet unobserved in- and output data.

FAU-Autoren / FAU-Herausgeber

Kreis, Oliver Dr.-Ing.
Niemann, Heinrich Prof. Dr.
Technische Fakultät


Deventer, R., Denzler, J., Niemann, H., & Kreis, O. (2003). Using test plans for bayesian modeling. In Perner P.; Rosenfeld A. (Eds.), Machine Learning and Data Mining in Pattern Recognition (pp. 307-316). Leipzig, DE: Berlin: Springer.

Deventer, Rainer, et al. "Using test plans for bayesian modeling." Proceedings of the Third International Conference, MLDM 2003, Leipzig Ed. Perner P.; Rosenfeld A., Berlin: Springer, 2003. 307-316.


Zuletzt aktualisiert 2019-20-04 um 14:50