Neural network models for anytime use

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

Abstract

Nowadays, the role of anytime and situational models and algorithms has become important because they offer a way to handle atypical situations and to overcome problems of resource, time, and data insuffiency in changing and time-critical systems and situations. Soft computing, in particular fuzzy and neural network based models are serious candidates for usage in such systems, however their high complexity, and in some cases unknown accuracy, can limit their applicability. In this paper, special neural network structures are introduced which (1) complexity can adaptively be chosen according to the temporal situation (resource, time, and data availability), (2) the accuracy is always known, and (3) monotonously decreases parallel with the increase of the complexity of the used model/algorithm.

Original languageEnglish
Title of host publicationINES 2011 - 15th International Conference on Intelligent Engineering Systems, Proceedings
Pages95-100
Number of pages6
DOIs
Publication statusPublished - 2011
Event15th International Conference on Intelligent Engineering Systems, INES 2011 - Poprad, Slovakia
Duration: Jun 23 2011Jun 25 2011

Other

Other15th International Conference on Intelligent Engineering Systems, INES 2011
CountrySlovakia
CityPoprad
Period6/23/116/25/11

Fingerprint

Neural networks
Soft computing
Availability

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Information Systems

Cite this

Várkonyi-Kóczy, A. (2011). Neural network models for anytime use. In INES 2011 - 15th International Conference on Intelligent Engineering Systems, Proceedings (pp. 95-100). [5954727] https://doi.org/10.1109/INES.2011.5954727

Neural network models for anytime use. / Várkonyi-Kóczy, A.

INES 2011 - 15th International Conference on Intelligent Engineering Systems, Proceedings. 2011. p. 95-100 5954727.

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

Várkonyi-Kóczy, A 2011, Neural network models for anytime use. in INES 2011 - 15th International Conference on Intelligent Engineering Systems, Proceedings., 5954727, pp. 95-100, 15th International Conference on Intelligent Engineering Systems, INES 2011, Poprad, Slovakia, 6/23/11. https://doi.org/10.1109/INES.2011.5954727
Várkonyi-Kóczy A. Neural network models for anytime use. In INES 2011 - 15th International Conference on Intelligent Engineering Systems, Proceedings. 2011. p. 95-100. 5954727 https://doi.org/10.1109/INES.2011.5954727
Várkonyi-Kóczy, A. / Neural network models for anytime use. INES 2011 - 15th International Conference on Intelligent Engineering Systems, Proceedings. 2011. pp. 95-100
@inproceedings{21acb26a47d349e0ba6a41bf18efbe0b,
title = "Neural network models for anytime use",
abstract = "Nowadays, the role of anytime and situational models and algorithms has become important because they offer a way to handle atypical situations and to overcome problems of resource, time, and data insuffiency in changing and time-critical systems and situations. Soft computing, in particular fuzzy and neural network based models are serious candidates for usage in such systems, however their high complexity, and in some cases unknown accuracy, can limit their applicability. In this paper, special neural network structures are introduced which (1) complexity can adaptively be chosen according to the temporal situation (resource, time, and data availability), (2) the accuracy is always known, and (3) monotonously decreases parallel with the increase of the complexity of the used model/algorithm.",
author = "A. V{\'a}rkonyi-K{\'o}czy",
year = "2011",
doi = "10.1109/INES.2011.5954727",
language = "English",
isbn = "9781424489565",
pages = "95--100",
booktitle = "INES 2011 - 15th International Conference on Intelligent Engineering Systems, Proceedings",

}

TY - GEN

T1 - Neural network models for anytime use

AU - Várkonyi-Kóczy, A.

PY - 2011

Y1 - 2011

N2 - Nowadays, the role of anytime and situational models and algorithms has become important because they offer a way to handle atypical situations and to overcome problems of resource, time, and data insuffiency in changing and time-critical systems and situations. Soft computing, in particular fuzzy and neural network based models are serious candidates for usage in such systems, however their high complexity, and in some cases unknown accuracy, can limit their applicability. In this paper, special neural network structures are introduced which (1) complexity can adaptively be chosen according to the temporal situation (resource, time, and data availability), (2) the accuracy is always known, and (3) monotonously decreases parallel with the increase of the complexity of the used model/algorithm.

AB - Nowadays, the role of anytime and situational models and algorithms has become important because they offer a way to handle atypical situations and to overcome problems of resource, time, and data insuffiency in changing and time-critical systems and situations. Soft computing, in particular fuzzy and neural network based models are serious candidates for usage in such systems, however their high complexity, and in some cases unknown accuracy, can limit their applicability. In this paper, special neural network structures are introduced which (1) complexity can adaptively be chosen according to the temporal situation (resource, time, and data availability), (2) the accuracy is always known, and (3) monotonously decreases parallel with the increase of the complexity of the used model/algorithm.

UR - http://www.scopus.com/inward/record.url?scp=80051739608&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80051739608&partnerID=8YFLogxK

U2 - 10.1109/INES.2011.5954727

DO - 10.1109/INES.2011.5954727

M3 - Conference contribution

SN - 9781424489565

SP - 95

EP - 100

BT - INES 2011 - 15th International Conference on Intelligent Engineering Systems, Proceedings

ER -