Error estimation of recurrent neural network models trained on a finite set of initial values

Binfan Liu; Jennie Si

Error estimation of recurrent neural network models trained on a finite set of initial values

Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper addresses the problem of estimating training error bounds of state and output trajectories for a class of recurrent neural networks as models of nonlinear dynamic systems. The bounds are obtained provided that the models have been trained on N trajectories with N independent random initial values which are uniformly distributed over [a, b] ^m ∈R ^m.

Original language	English (US)
Title of host publication	Proceedings of the IEEE Conference on Decision and Control
Publisher	IEEE
Pages	1574-1578
Number of pages	5
Volume	2
State	Published - 1997
Event	Proceedings of the 1997 36th IEEE Conference on Decision and Control. Part 1 (of 5) - San Diego, CA, USA Duration: Dec 10 1997 → Dec 12 1997

Other

Other	Proceedings of the 1997 36th IEEE Conference on Decision and Control. Part 1 (of 5)
City	San Diego, CA, USA
Period	12/10/97 → 12/12/97

ASJC Scopus subject areas

Chemical Health and Safety
Control and Systems Engineering
Safety, Risk, Reliability and Quality

Cite this

@inproceedings{a8f03ca5f29e442cbcf6fe92ed5ee0eb,

title = "Error estimation of recurrent neural network models trained on a finite set of initial values",

abstract = "This paper addresses the problem of estimating training error bounds of state and output trajectories for a class of recurrent neural networks as models of nonlinear dynamic systems. The bounds are obtained provided that the models have been trained on N trajectories with N independent random initial values which are uniformly distributed over [a, b] m ∈R m. ",

author = "Binfan Liu and Jennie Si",

year = "1997",

language = "English (US)",

volume = "2",

pages = "1574--1578",

booktitle = "Proceedings of the IEEE Conference on Decision and Control",

publisher = "IEEE",

note = "Proceedings of the 1997 36th IEEE Conference on Decision and Control. Part 1 (of 5) ; Conference date: 10-12-1997 Through 12-12-1997",

}

TY - GEN

T1 - Error estimation of recurrent neural network models trained on a finite set of initial values

AU - Liu, Binfan

AU - Si, Jennie

PY - 1997

Y1 - 1997

N2 - This paper addresses the problem of estimating training error bounds of state and output trajectories for a class of recurrent neural networks as models of nonlinear dynamic systems. The bounds are obtained provided that the models have been trained on N trajectories with N independent random initial values which are uniformly distributed over [a, b] m ∈R m.

AB - This paper addresses the problem of estimating training error bounds of state and output trajectories for a class of recurrent neural networks as models of nonlinear dynamic systems. The bounds are obtained provided that the models have been trained on N trajectories with N independent random initial values which are uniformly distributed over [a, b] m ∈R m.

UR - http://www.scopus.com/inward/record.url?scp=0031349221&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031349221&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0031349221

VL - 2

SP - 1574

EP - 1578

BT - Proceedings of the IEEE Conference on Decision and Control

PB - IEEE

T2 - Proceedings of the 1997 36th IEEE Conference on Decision and Control. Part 1 (of 5)

Y2 - 10 December 1997 through 12 December 1997

ER -

Error estimation of recurrent neural network models trained on a finite set of initial values

Abstract

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this