Global learning algorithms for discrete-time cellular neural networks

Holger Magnussen; Josef A. Nossek

Global learning algorithms for discrete-time cellular neural networks

Holger Magnussen
, Josef A. Nossek

Chair of Circuit Theory and Signal Processing (2008 — 2021)

Technical University of Munich

Research output: Contribution to conference › Paper › peer-review

8 Scopus citations

Abstract

Two learning algorithms for Discrete-Time Cellular Neural Networks (DTCNNs) are proposed, which do not require the a priori knowledge of the output trajectory of the network. A cost function is defined, which is minimized by Direct Search optimization methods and Simulated Annealing. Applications of the algorithms are presented in a companion paper.

Original language	English
Pages	165-170
Number of pages	6
State	Published - 1994
Event	Proceedings of the 3rd IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94) - Rome, Italy Duration: 18 Dec 1994 → 21 Dec 1994

Conference

Conference	Proceedings of the 3rd IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94)
City	Rome, Italy
Period	18/12/94 → 21/12/94

Cite this

@conference{066088cb35ba467384b7b80d7bc2a2a0,

title = "Global learning algorithms for discrete-time cellular neural networks",

abstract = "Two learning algorithms for Discrete-Time Cellular Neural Networks (DTCNNs) are proposed, which do not require the a priori knowledge of the output trajectory of the network. A cost function is defined, which is minimized by Direct Search optimization methods and Simulated Annealing. Applications of the algorithms are presented in a companion paper.",

author = "Holger Magnussen and Nossek, \{Josef A.\}",

year = "1994",

language = "English",

pages = "165--170",

note = "Proceedings of the 3rd IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94) ; Conference date: 18-12-1994 Through 21-12-1994",

}

TY - CONF

T1 - Global learning algorithms for discrete-time cellular neural networks

AU - Magnussen, Holger

AU - Nossek, Josef A.

PY - 1994

Y1 - 1994

N2 - Two learning algorithms for Discrete-Time Cellular Neural Networks (DTCNNs) are proposed, which do not require the a priori knowledge of the output trajectory of the network. A cost function is defined, which is minimized by Direct Search optimization methods and Simulated Annealing. Applications of the algorithms are presented in a companion paper.

AB - Two learning algorithms for Discrete-Time Cellular Neural Networks (DTCNNs) are proposed, which do not require the a priori knowledge of the output trajectory of the network. A cost function is defined, which is minimized by Direct Search optimization methods and Simulated Annealing. Applications of the algorithms are presented in a companion paper.

UR - https://www.scopus.com/pages/publications/0028738751

M3 - Paper

AN - SCOPUS:0028738751

SP - 165

EP - 170

T2 - Proceedings of the 3rd IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94)

Y2 - 18 December 1994 through 21 December 1994

ER -

Global learning algorithms for discrete-time cellular neural networks

Abstract

Conference

Other files and links

Fingerprint

Cite this