Queral networks: Toward an approach for engineering large artificial neural networks

Travis A. Hoffman, Jerzy W Rozenblit, Ali Akoglu, Liana Suantak

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

A generalization of an artificial neuron is introduced in this paper. Called the queron1, this abstraction is the basic computational node of Queral Networks (QN). QNs are introduced as a parallel architecture expected to be an improvement upon Artificial Neural Networks (ANN). The fundamental properties of QNs are presented here: reusability, complexity management and human-readability. It is expected that this proposed architecture will allow the engineering of large, highly parallel computer systems with the computational benefits of ANNs while overcoming the challenge of developing ANNs. A brief case study is given to illustrate the QN concept.

Original languageEnglish (US)
Title of host publicationProceedings - 18th IEEE International Conference and Workshops on Engineering of Computer-Based Systems, ECBS 2011
Pages81-88
Number of pages8
DOIs
StatePublished - 2011
Event18th IEEE International Conference and Workshops on Engineering of Computer-Based Systems, ECBS 2011 - Las Vegas, NV, United States
Duration: Apr 27 2011Apr 29 2011

Other

Other18th IEEE International Conference and Workshops on Engineering of Computer-Based Systems, ECBS 2011
CountryUnited States
CityLas Vegas, NV
Period4/27/114/29/11

Fingerprint

Parallel architectures
Reusability
Neurons
Computer systems
Neural networks

Keywords

  • Artificial Neural Networks
  • Automatic programming
  • Computation theory
  • Evolutionary computation
  • Parallel architecture

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems

Cite this

Hoffman, T. A., Rozenblit, J. W., Akoglu, A., & Suantak, L. (2011). Queral networks: Toward an approach for engineering large artificial neural networks. In Proceedings - 18th IEEE International Conference and Workshops on Engineering of Computer-Based Systems, ECBS 2011 (pp. 81-88). [5934807] https://doi.org/10.1109/ECBS.2011.27

Queral networks : Toward an approach for engineering large artificial neural networks. / Hoffman, Travis A.; Rozenblit, Jerzy W; Akoglu, Ali; Suantak, Liana.

Proceedings - 18th IEEE International Conference and Workshops on Engineering of Computer-Based Systems, ECBS 2011. 2011. p. 81-88 5934807.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hoffman, TA, Rozenblit, JW, Akoglu, A & Suantak, L 2011, Queral networks: Toward an approach for engineering large artificial neural networks. in Proceedings - 18th IEEE International Conference and Workshops on Engineering of Computer-Based Systems, ECBS 2011., 5934807, pp. 81-88, 18th IEEE International Conference and Workshops on Engineering of Computer-Based Systems, ECBS 2011, Las Vegas, NV, United States, 4/27/11. https://doi.org/10.1109/ECBS.2011.27
Hoffman TA, Rozenblit JW, Akoglu A, Suantak L. Queral networks: Toward an approach for engineering large artificial neural networks. In Proceedings - 18th IEEE International Conference and Workshops on Engineering of Computer-Based Systems, ECBS 2011. 2011. p. 81-88. 5934807 https://doi.org/10.1109/ECBS.2011.27
Hoffman, Travis A. ; Rozenblit, Jerzy W ; Akoglu, Ali ; Suantak, Liana. / Queral networks : Toward an approach for engineering large artificial neural networks. Proceedings - 18th IEEE International Conference and Workshops on Engineering of Computer-Based Systems, ECBS 2011. 2011. pp. 81-88
@inproceedings{07ef9167b34f49088454ae0f37c2812e,
title = "Queral networks: Toward an approach for engineering large artificial neural networks",
abstract = "A generalization of an artificial neuron is introduced in this paper. Called the queron1, this abstraction is the basic computational node of Queral Networks (QN). QNs are introduced as a parallel architecture expected to be an improvement upon Artificial Neural Networks (ANN). The fundamental properties of QNs are presented here: reusability, complexity management and human-readability. It is expected that this proposed architecture will allow the engineering of large, highly parallel computer systems with the computational benefits of ANNs while overcoming the challenge of developing ANNs. A brief case study is given to illustrate the QN concept.",
keywords = "Artificial Neural Networks, Automatic programming, Computation theory, Evolutionary computation, Parallel architecture",
author = "Hoffman, {Travis A.} and Rozenblit, {Jerzy W} and Ali Akoglu and Liana Suantak",
year = "2011",
doi = "10.1109/ECBS.2011.27",
language = "English (US)",
isbn = "9780769543796",
pages = "81--88",
booktitle = "Proceedings - 18th IEEE International Conference and Workshops on Engineering of Computer-Based Systems, ECBS 2011",

}

TY - GEN

T1 - Queral networks

T2 - Toward an approach for engineering large artificial neural networks

AU - Hoffman, Travis A.

AU - Rozenblit, Jerzy W

AU - Akoglu, Ali

AU - Suantak, Liana

PY - 2011

Y1 - 2011

N2 - A generalization of an artificial neuron is introduced in this paper. Called the queron1, this abstraction is the basic computational node of Queral Networks (QN). QNs are introduced as a parallel architecture expected to be an improvement upon Artificial Neural Networks (ANN). The fundamental properties of QNs are presented here: reusability, complexity management and human-readability. It is expected that this proposed architecture will allow the engineering of large, highly parallel computer systems with the computational benefits of ANNs while overcoming the challenge of developing ANNs. A brief case study is given to illustrate the QN concept.

AB - A generalization of an artificial neuron is introduced in this paper. Called the queron1, this abstraction is the basic computational node of Queral Networks (QN). QNs are introduced as a parallel architecture expected to be an improvement upon Artificial Neural Networks (ANN). The fundamental properties of QNs are presented here: reusability, complexity management and human-readability. It is expected that this proposed architecture will allow the engineering of large, highly parallel computer systems with the computational benefits of ANNs while overcoming the challenge of developing ANNs. A brief case study is given to illustrate the QN concept.

KW - Artificial Neural Networks

KW - Automatic programming

KW - Computation theory

KW - Evolutionary computation

KW - Parallel architecture

UR - http://www.scopus.com/inward/record.url?scp=80052015037&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052015037&partnerID=8YFLogxK

U2 - 10.1109/ECBS.2011.27

DO - 10.1109/ECBS.2011.27

M3 - Conference contribution

AN - SCOPUS:80052015037

SN - 9780769543796

SP - 81

EP - 88

BT - Proceedings - 18th IEEE International Conference and Workshops on Engineering of Computer-Based Systems, ECBS 2011

ER -