Finding the Optimal Continuous Model for Discrete Data by Neural Network Interpolation of Fractional Iteration


Contact
lkindermann [ at ] awi-bremerhaven.de

Abstract

Given the complete knowledge of the state variables of a dynamicalsystem at fixed intervals, it is possible to construct a mapping, which is a perfectdiscrete time model of the system. To embed this into a continuum, the translationequation has to be solved for this mapping. However, in general, neitherexistence nor uniqueness of solutions can be guaranteed, but fractional iteratesof the mapping computed by a neural network can provide regularized solutionsthat exactly comply with the laws of physics for several examples. Here weextend this method to continuous embeddings which represent the true trajectoriesof the dynamical system.



Item Type
Article
Authors
Divisions
Programs
Peer revision
ISI/Scopus peer-reviewed
Publication Status
Published
Eprint ID
10376
Cite as
Kindermann, L. , Lewandowski, A. and Protzel, P. (2002): Finding the Optimal Continuous Model for Discrete Data by Neural Network Interpolation of Fractional Iteration , Lecture notes in computer science, 2415 , pp. 1094-1099 .


Share

Research Platforms
N/A

Campaigns


Actions
Edit Item Edit Item