Pareto-optimal noise and approximation properties of RBFnetworks
Eickhoff R, Rückert U (2006)
In: Proceedings of the 16th International Conference on Artificial Neural Networks (ICANN). Kollias S (Ed); Athens, Greece: Springer Berlin Heidelberg: pp.:993-1002.
Konferenzbeitrag
| Veröffentlicht | Englisch
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Autor*in
Eickhoff, Ralf;
Rückert, UlrichUniBi
Herausgeber*in
Kollias, Stefanos
Abstract / Bemerkung
Neural networks are intended to be robust to noise and tolerant
to failures in their architecture. Therefore, these systems are particularly
interesting to be integrated in hardware and to be operating
under noisy environment. In this work, measurements are introduced
which can decrease the sensitivity of Radial Basis Function networks to
noise without any degradation in their approximation capability. For this
purpose, pareto-optimal solutions are determined for the parameters of
the network.
Erscheinungsjahr
2006
Titel des Konferenzbandes
Proceedings of the 16th International Conference on Artificial Neural Networks (ICANN)
Seite(n)
pp.:993-1002
ISBN
9783540386254
ISSN
0302-9743
Page URI
https://pub.uni-bielefeld.de/record/2289026
Zitieren
Eickhoff R, Rückert U. Pareto-optimal noise and approximation properties of RBFnetworks. In: Kollias S, ed. Proceedings of the 16th International Conference on Artificial Neural Networks (ICANN). Athens, Greece: Springer Berlin Heidelberg; 2006: pp.:993-1002.
Eickhoff, R., & Rückert, U. (2006). Pareto-optimal noise and approximation properties of RBFnetworks. In S. Kollias (Ed.), Proceedings of the 16th International Conference on Artificial Neural Networks (ICANN) (pp. pp.:993-1002). Athens, Greece: Springer Berlin Heidelberg. https://doi.org/10.1007/11840817_103
Eickhoff, Ralf, and Rückert, Ulrich. 2006. “Pareto-optimal noise and approximation properties of RBFnetworks”. In Proceedings of the 16th International Conference on Artificial Neural Networks (ICANN), ed. Stefanos Kollias, pp.:993-1002. Athens, Greece: Springer Berlin Heidelberg.
Eickhoff, R., and Rückert, U. (2006). “Pareto-optimal noise and approximation properties of RBFnetworks” in Proceedings of the 16th International Conference on Artificial Neural Networks (ICANN), Kollias, S. ed. (Athens, Greece: Springer Berlin Heidelberg), pp.:993-1002.
Eickhoff, R., & Rückert, U., 2006. Pareto-optimal noise and approximation properties of RBFnetworks. In S. Kollias, ed. Proceedings of the 16th International Conference on Artificial Neural Networks (ICANN). Athens, Greece: Springer Berlin Heidelberg, pp. pp.:993-1002.
R. Eickhoff and U. Rückert, “Pareto-optimal noise and approximation properties of RBFnetworks”, Proceedings of the 16th International Conference on Artificial Neural Networks (ICANN), S. Kollias, ed., Athens, Greece: Springer Berlin Heidelberg, 2006, pp.pp.:993-1002.
Eickhoff, R., Rückert, U.: Pareto-optimal noise and approximation properties of RBFnetworks. In: Kollias, S. (ed.) Proceedings of the 16th International Conference on Artificial Neural Networks (ICANN). p. pp.:993-1002. Springer Berlin Heidelberg, Athens, Greece (2006).
Eickhoff, Ralf, and Rückert, Ulrich. “Pareto-optimal noise and approximation properties of RBFnetworks”. Proceedings of the 16th International Conference on Artificial Neural Networks (ICANN). Ed. Stefanos Kollias. Athens, Greece: Springer Berlin Heidelberg, 2006. pp.:993-1002.
Google Scholar
ISBN Suche