ERROR ESTIMATION OF RECURRENT NEURAL-NETWORK MODELS TRAINED ON A FINITE-SET OF INITIAL VALUES

Authors
LIU BF SI J
Citation
Bf. Liu et J. Si, ERROR ESTIMATION OF RECURRENT NEURAL-NETWORK MODELS TRAINED ON A FINITE-SET OF INITIAL VALUES, IEEE transactions on circuits and systems. 1, Fundamental theory andapplications, 44(11), 1997, pp. 1086-1089
Citations number
7
Categorie Soggetti
Engineering, Eletrical & Electronic
Journal title
IEEE transactions on circuits and systems. 1, Fundamental theory andapplications → ACNP
ISSN journal
10577122
Volume
44
Issue
11
Year of publication
1997
Pages
1086 - 1089
Database
ISI
SICI code
1057-7122(1997)44:11<1086:EEORNM>2.0.ZU;2-F
Abstract
This letter addresses the problem of estimating training error bounds of state and output trajectories for a class of recurrent neural netwo rks as models of nonlinear dynamic systems, The bounds are obtained pr ovided that the models have been trained on N trajectories with N inde pendent random initial values which are uniformly distributed over [a, b](m) is an element of R-m.