Application of prony signal analysis to recurrent neural networks

Mohammad Farrokhi; Can Isik

doi:10.1109/icnn.1994.374198

Application of prony signal analysis to recurrent neural networks

Mohammad Farrokhi, Can Isik

Department of Electrical Engineering & Computer Science

Research output: Chapter in Book/Entry/Poem › Conference contribution

Abstract

Recurrent neural networks are highly nonlinear dynamic systems, and therefore it is not an easy task to analyze their dynamic behavior. The primary goal of this paper is to apply Prony signal analysis and a modified root locus technique to recurrent neural networks. Prony method is compared with other linearization methods to analyze recurrent neural networks, and their performances are demonstrated using simulated examples.

Original language	English (US)
Title of host publication	IEEE International Conference on Neural Networks - Conference Proceedings
Publisher	IEEE Computer Society
Pages	413-418
Number of pages	6
ISBN (Print)	078031901X
DOIs	https://doi.org/10.1109/icnn.1994.374198
State	Published - 1994
Event	Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) - Orlando, FL, USA Duration: Jun 27 1994 → Jun 29 1994

Publication series

Name	IEEE International Conference on Neural Networks - Conference Proceedings
Volume	1

Other

Other	Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7)
City	Orlando, FL, USA
Period	6/27/94 → 6/29/94

ASJC Scopus subject areas

Software

Access to Document

10.1109/icnn.1994.374198

Cite this

Application of prony signal analysis to recurrent neural networks. / Farrokhi, Mohammad; Isik, Can.
IEEE International Conference on Neural Networks - Conference Proceedings. IEEE Computer Society, 1994. p. 413-418 (IEEE International Conference on Neural Networks - Conference Proceedings; Vol. 1).

Research output: Chapter in Book/Entry/Poem › Conference contribution

Farrokhi, M & Isik, C 1994, Application of prony signal analysis to recurrent neural networks. in IEEE International Conference on Neural Networks - Conference Proceedings. IEEE International Conference on Neural Networks - Conference Proceedings, vol. 1, IEEE Computer Society, pp. 413-418, Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7), Orlando, FL, USA, 6/27/94. https://doi.org/10.1109/icnn.1994.374198

@inproceedings{a58cdcf0f12d439ea2a2625485ff1865,

title = "Application of prony signal analysis to recurrent neural networks",

abstract = "Recurrent neural networks are highly nonlinear dynamic systems, and therefore it is not an easy task to analyze their dynamic behavior. The primary goal of this paper is to apply Prony signal analysis and a modified root locus technique to recurrent neural networks. Prony method is compared with other linearization methods to analyze recurrent neural networks, and their performances are demonstrated using simulated examples.",

author = "Mohammad Farrokhi and Can Isik",

year = "1994",

doi = "10.1109/icnn.1994.374198",

language = "English (US)",

isbn = "078031901X",

series = "IEEE International Conference on Neural Networks - Conference Proceedings",

publisher = "IEEE Computer Society",

pages = "413--418",

booktitle = "IEEE International Conference on Neural Networks - Conference Proceedings",

address = "United States",

note = "Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) ; Conference date: 27-06-1994 Through 29-06-1994",

}

TY - GEN

T1 - Application of prony signal analysis to recurrent neural networks

AU - Farrokhi, Mohammad

AU - Isik, Can

PY - 1994

Y1 - 1994

N2 - Recurrent neural networks are highly nonlinear dynamic systems, and therefore it is not an easy task to analyze their dynamic behavior. The primary goal of this paper is to apply Prony signal analysis and a modified root locus technique to recurrent neural networks. Prony method is compared with other linearization methods to analyze recurrent neural networks, and their performances are demonstrated using simulated examples.

AB - Recurrent neural networks are highly nonlinear dynamic systems, and therefore it is not an easy task to analyze their dynamic behavior. The primary goal of this paper is to apply Prony signal analysis and a modified root locus technique to recurrent neural networks. Prony method is compared with other linearization methods to analyze recurrent neural networks, and their performances are demonstrated using simulated examples.

UR - http://www.scopus.com/inward/record.url?scp=0028731589&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0028731589&partnerID=8YFLogxK

U2 - 10.1109/icnn.1994.374198

DO - 10.1109/icnn.1994.374198

M3 - Conference contribution

AN - SCOPUS:0028731589

SN - 078031901X

T3 - IEEE International Conference on Neural Networks - Conference Proceedings

SP - 413

EP - 418

BT - IEEE International Conference on Neural Networks - Conference Proceedings

PB - IEEE Computer Society

T2 - Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7)

Y2 - 27 June 1994 through 29 June 1994

ER -

Application of prony signal analysis to recurrent neural networks

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this