On tensor-product model based representation of neural networks

András Rövid, L. Szeidl, P. Várlaki

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

8 Citations (Scopus)

Abstract

The approximation methods of mathematics are widely used in theory and practice for several problems. In the framework of the paper a novel tensor-product based approach for representation of neural networks (NNs) is proposed. The NNs in this case stand for local models based on which a more complex parameter varying model can numerically be reconstructed and reduced using the higher order singular value decomposition (HOSVD). The HOSVD as well as the tensor-product based representation of NNs will be discussed in detail.

Original languageEnglish
Title of host publicationINES 2011 - 15th International Conference on Intelligent Engineering Systems, Proceedings
Pages69-72
Number of pages4
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

Tensors
Singular value decomposition
Neural networks

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Information Systems

Cite this

Rövid, A., Szeidl, L., & Várlaki, P. (2011). On tensor-product model based representation of neural networks. In INES 2011 - 15th International Conference on Intelligent Engineering Systems, Proceedings (pp. 69-72). [5954721] https://doi.org/10.1109/INES.2011.5954721

On tensor-product model based representation of neural networks. / Rövid, András; Szeidl, L.; Várlaki, P.

INES 2011 - 15th International Conference on Intelligent Engineering Systems, Proceedings. 2011. p. 69-72 5954721.

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

Rövid, A, Szeidl, L & Várlaki, P 2011, On tensor-product model based representation of neural networks. in INES 2011 - 15th International Conference on Intelligent Engineering Systems, Proceedings., 5954721, pp. 69-72, 15th International Conference on Intelligent Engineering Systems, INES 2011, Poprad, Slovakia, 6/23/11. https://doi.org/10.1109/INES.2011.5954721
Rövid A, Szeidl L, Várlaki P. On tensor-product model based representation of neural networks. In INES 2011 - 15th International Conference on Intelligent Engineering Systems, Proceedings. 2011. p. 69-72. 5954721 https://doi.org/10.1109/INES.2011.5954721
Rövid, András ; Szeidl, L. ; Várlaki, P. / On tensor-product model based representation of neural networks. INES 2011 - 15th International Conference on Intelligent Engineering Systems, Proceedings. 2011. pp. 69-72
@inproceedings{a4b6633a936742c6bb2ed1389a96b2fb,
title = "On tensor-product model based representation of neural networks",
abstract = "The approximation methods of mathematics are widely used in theory and practice for several problems. In the framework of the paper a novel tensor-product based approach for representation of neural networks (NNs) is proposed. The NNs in this case stand for local models based on which a more complex parameter varying model can numerically be reconstructed and reduced using the higher order singular value decomposition (HOSVD). The HOSVD as well as the tensor-product based representation of NNs will be discussed in detail.",
author = "Andr{\'a}s R{\"o}vid and L. Szeidl and P. V{\'a}rlaki",
year = "2011",
doi = "10.1109/INES.2011.5954721",
language = "English",
isbn = "9781424489565",
pages = "69--72",
booktitle = "INES 2011 - 15th International Conference on Intelligent Engineering Systems, Proceedings",

}

TY - GEN

T1 - On tensor-product model based representation of neural networks

AU - Rövid, András

AU - Szeidl, L.

AU - Várlaki, P.

PY - 2011

Y1 - 2011

N2 - The approximation methods of mathematics are widely used in theory and practice for several problems. In the framework of the paper a novel tensor-product based approach for representation of neural networks (NNs) is proposed. The NNs in this case stand for local models based on which a more complex parameter varying model can numerically be reconstructed and reduced using the higher order singular value decomposition (HOSVD). The HOSVD as well as the tensor-product based representation of NNs will be discussed in detail.

AB - The approximation methods of mathematics are widely used in theory and practice for several problems. In the framework of the paper a novel tensor-product based approach for representation of neural networks (NNs) is proposed. The NNs in this case stand for local models based on which a more complex parameter varying model can numerically be reconstructed and reduced using the higher order singular value decomposition (HOSVD). The HOSVD as well as the tensor-product based representation of NNs will be discussed in detail.

UR - http://www.scopus.com/inward/record.url?scp=80051768061&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80051768061&partnerID=8YFLogxK

U2 - 10.1109/INES.2011.5954721

DO - 10.1109/INES.2011.5954721

M3 - Conference contribution

AN - SCOPUS:80051768061

SN - 9781424489565

SP - 69

EP - 72

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

ER -