Existence and Global Attractivity of Stable Solutions in Neural Networks

Patrick Leoni () and Pietro Senesi

No 198, IEW - Working Papers from Institute for Empirical Research in Economics - University of Zurich

Abstract: The present paper shows that a su�cient condition for the existence of a stable solution to an autoregressive neural network model is the continuity and boundedness of the activation function of the hidden units in the multi layer perceptron (MLP). In addition, uniqueness of a stable solution is ensured by global lipschitzness and some conditions on the parameters of the system. In this case, the stable value is globally stable and convergence of the learning process occurs at exponential rate.

Keywords: Neural Networks; Stable Value (search for similar items in EconPapers)
JEL-codes: C45 (search for similar items in EconPapers)
New Economics Papers: this item is included in nep-cmp
References: View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.zora.uzh.ch/id/eprint/52093/1/iewwp198.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:zur:iewwpx:198

Access Statistics for this paper

More papers in IEW - Working Papers from Institute for Empirical Research in Economics - University of Zurich
Bibliographic data for series maintained by Severin Oswald ().