On the Use of Local RBF Networks to Approximate Multivalued Functions and Relations

Autor: Hahn, Klaus, Waschulzik, T.

A connectionist model made up of a combination of RBF networks is proposed; the model decomposes multivalued dependencies into local single valued functions; theory and applications are presented.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::422c3c83918a6489d23338b687c59164

Quality-assured Efficient Engineering of Feedforward Neural Networks (QUEEN) -- pretherapeutic estimation of lymph node status in patients with gastric carcinoma.

Autor: Hensler, K., Waschulzik, T., Mönig, S. P., Maruyama, K., Hölscher, A. H., Bollschweiler, E., Mönig, S P, Hölscher, A H

Publikováno v: Methods of Information in Medicine; 2005, Vol. 44 Issue 5, p647-654, 8p

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Quality assured efficient engineering of feedforward neural networks with supervised learning (QUEEN) evaluated with the“pima indians diabetes database”.

Autor: Waschulzik, T., Brauer, W., Castedello, T., Henery, B.

Publikováno v: Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges & Perspectives for the New Millennium; 2000, p97-97, 1p

Temporal resolution: a critical parameter in simulations of pulse-coupled neural networks.

Autor: Kraut, U., Nischwitz, A., Waschulzik, T.

Publikováno v: Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan); 1993, Issue 2, p1116-1116, 1p