Emergence of computational chaos in asynchronous neurocomputing

Sarit Barhen; Vladimir Protopopescu; Jack Wells; Neena Imam; Jacob Barhen

doi:10.1109/IJCNN.2004.1380916

Emergence of computational chaos in asynchronous neurocomputing

Sarit Barhen, Vladimir Protopopescu, Jack Wells, Neena Imam, Jacob Barhen

Computational Sciences & Engineering Div

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

1 Scopus citations

Abstract

One of the most important features of artificial neural networks in emerging, brain-inspired, nanoarchitectural design is their inherent ability to perform massively parallel, nonlinear signal processing. When operating in a system-wide asynchronous regime, such networks may exhibit a phenomenon referred to as "computational chaos", which impedes the efficient retrieval of information usually stored in the system's attractors. In this paper, we illustrate the emergence of computational chaos from fixed point and limit cycle attractors for node communication delays in a widely used neural network model. In particular, the complete Lyapunov spectrum associated with the network dynamics is computed, and conditions that prevent the emergence of chaos are derived.

Original language	English
Title of host publication	2004 IEEE International Joint Conference on Neural Networks - Proceedings
Pages	1971-1976
Number of pages	6
DOIs	https://doi.org/10.1109/IJCNN.2004.1380916
State	Published - 2004
Event	2004 IEEE International Joint Conference on Neural Networks - Proceedings - Budapest, Hungary Duration: Jul 25 2004 → Jul 29 2004

Publication series

Name	IEEE International Conference on Neural Networks - Conference Proceedings
Volume	3
ISSN (Print)	1098-7576

Conference

Conference	2004 IEEE International Joint Conference on Neural Networks - Proceedings
Country/Territory	Hungary
City	Budapest
Period	07/25/04 → 07/29/04

Keywords

Asynchronous computing
Computational chaos
Lyapunov spectrum
Neural networks

Access to Document

10.1109/IJCNN.2004.1380916

Cite this

@inproceedings{e61c431899e3433792f870c4ed6ee6b3,

title = "Emergence of computational chaos in asynchronous neurocomputing",

abstract = "One of the most important features of artificial neural networks in emerging, brain-inspired, nanoarchitectural design is their inherent ability to perform massively parallel, nonlinear signal processing. When operating in a system-wide asynchronous regime, such networks may exhibit a phenomenon referred to as {"}computational chaos{"}, which impedes the efficient retrieval of information usually stored in the system's attractors. In this paper, we illustrate the emergence of computational chaos from fixed point and limit cycle attractors for node communication delays in a widely used neural network model. In particular, the complete Lyapunov spectrum associated with the network dynamics is computed, and conditions that prevent the emergence of chaos are derived.",

keywords = "Asynchronous computing, Computational chaos, Lyapunov spectrum, Neural networks",

author = "Sarit Barhen and Vladimir Protopopescu and Jack Wells and Neena Imam and Jacob Barhen",

year = "2004",

doi = "10.1109/IJCNN.2004.1380916",

language = "English",

isbn = "0780383591",

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

pages = "1971--1976",

booktitle = "2004 IEEE International Joint Conference on Neural Networks - Proceedings",

note = "2004 IEEE International Joint Conference on Neural Networks - Proceedings ; Conference date: 25-07-2004 Through 29-07-2004",

}

Barhen, S, Protopopescu, V, Wells, J, Imam, N & Barhen, J 2004, Emergence of computational chaos in asynchronous neurocomputing. in 2004 IEEE International Joint Conference on Neural Networks - Proceedings. IEEE International Conference on Neural Networks - Conference Proceedings, vol. 3, pp. 1971-1976, 2004 IEEE International Joint Conference on Neural Networks - Proceedings, Budapest, Hungary, 07/25/04. https://doi.org/10.1109/IJCNN.2004.1380916

Emergence of computational chaos in asynchronous neurocomputing. / Barhen, Sarit; Protopopescu, Vladimir; Wells, Jack et al.
2004 IEEE International Joint Conference on Neural Networks - Proceedings. 2004. p. 1971-1976 (IEEE International Conference on Neural Networks - Conference Proceedings; Vol. 3).

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

TY - GEN

T1 - Emergence of computational chaos in asynchronous neurocomputing

AU - Barhen, Sarit

AU - Protopopescu, Vladimir

AU - Wells, Jack

AU - Imam, Neena

AU - Barhen, Jacob

PY - 2004

Y1 - 2004

N2 - One of the most important features of artificial neural networks in emerging, brain-inspired, nanoarchitectural design is their inherent ability to perform massively parallel, nonlinear signal processing. When operating in a system-wide asynchronous regime, such networks may exhibit a phenomenon referred to as "computational chaos", which impedes the efficient retrieval of information usually stored in the system's attractors. In this paper, we illustrate the emergence of computational chaos from fixed point and limit cycle attractors for node communication delays in a widely used neural network model. In particular, the complete Lyapunov spectrum associated with the network dynamics is computed, and conditions that prevent the emergence of chaos are derived.

AB - One of the most important features of artificial neural networks in emerging, brain-inspired, nanoarchitectural design is their inherent ability to perform massively parallel, nonlinear signal processing. When operating in a system-wide asynchronous regime, such networks may exhibit a phenomenon referred to as "computational chaos", which impedes the efficient retrieval of information usually stored in the system's attractors. In this paper, we illustrate the emergence of computational chaos from fixed point and limit cycle attractors for node communication delays in a widely used neural network model. In particular, the complete Lyapunov spectrum associated with the network dynamics is computed, and conditions that prevent the emergence of chaos are derived.

KW - Asynchronous computing

KW - Computational chaos

KW - Lyapunov spectrum

KW - Neural networks

UR - http://www.scopus.com/inward/record.url?scp=10844254850&partnerID=8YFLogxK

U2 - 10.1109/IJCNN.2004.1380916

DO - 10.1109/IJCNN.2004.1380916

M3 - Conference contribution

AN - SCOPUS:10844254850

SN - 0780383591

T3 - IEEE International Conference on Neural Networks - Conference Proceedings

SP - 1971

EP - 1976

BT - 2004 IEEE International Joint Conference on Neural Networks - Proceedings

T2 - 2004 IEEE International Joint Conference on Neural Networks - Proceedings

Y2 - 25 July 2004 through 29 July 2004

ER -

Emergence of computational chaos in asynchronous neurocomputing

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this