Optimal solutions of selected cellular neural network applications by the hardware annealing method

Bing J. Sheu; Sa H. Bang; Wai-Chi  Fang

doi:10.1109/CNNA.1994.381666

Optimal solutions of selected cellular neural network applications by the hardware annealing method

Bing J. Sheu^*, Sa H. Bang, Wai-Chi Fang

^*Corresponding author for this work

Institute of Electronics

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

2 Scopus citations

Abstract

An engineering annealing method for optimal solutions of cellular neural networks is presented. Cellular neural networks, have great potential in solving many important scientific problems in signal processing and optimization by the use of pre-determined templates. Hardware annealing, which is a paralleled version of effective mean-field annealing in analog networks, is a highly efficient method of finding optimal solutions for cellular neural networks. It does not require any stochastic procedure and henceforth can be very fast. The generalized energy function of the network is first increased by reducing the voltage gain of each neuron. Then, the hardware annealing searches for the globally minimum energy state by continuously increasing the gain of neurons. The process of global optimization by the proposed hardware annealing method can be described by eigenvalues in the time-varying dynamic system.

Original language	English
Pages	279-284
Number of pages	6
DOIs	https://doi.org/10.1109/CNNA.1994.381666
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

Access to Document

10.1109/CNNA.1994.381666

Cite this

@conference{d701142a50374d64a1e6ebab611bb02b,

title = "Optimal solutions of selected cellular neural network applications by the hardware annealing method",

abstract = "An engineering annealing method for optimal solutions of cellular neural networks is presented. Cellular neural networks, have great potential in solving many important scientific problems in signal processing and optimization by the use of pre-determined templates. Hardware annealing, which is a paralleled version of effective mean-field annealing in analog networks, is a highly efficient method of finding optimal solutions for cellular neural networks. It does not require any stochastic procedure and henceforth can be very fast. The generalized energy function of the network is first increased by reducing the voltage gain of each neuron. Then, the hardware annealing searches for the globally minimum energy state by continuously increasing the gain of neurons. The process of global optimization by the proposed hardware annealing method can be described by eigenvalues in the time-varying dynamic system.",

author = "Sheu, {Bing J.} and Bang, {Sa H.} and Wai-Chi Fang",

year = "1994",

doi = "10.1109/CNNA.1994.381666",

language = "English",

pages = "279--284",

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",

}

Optimal solutions of selected cellular neural network applications by the hardware annealing method. / Sheu, Bing J.; Bang, Sa H.; Fang, Wai-Chi .
1994. 279-284 Paper presented at Proceedings of the 3rd IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA-94), Rome, Italy.

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

TY - CONF

T1 - Optimal solutions of selected cellular neural network applications by the hardware annealing method

AU - Sheu, Bing J.

AU - Bang, Sa H.

AU - Fang, Wai-Chi

PY - 1994

Y1 - 1994

N2 - An engineering annealing method for optimal solutions of cellular neural networks is presented. Cellular neural networks, have great potential in solving many important scientific problems in signal processing and optimization by the use of pre-determined templates. Hardware annealing, which is a paralleled version of effective mean-field annealing in analog networks, is a highly efficient method of finding optimal solutions for cellular neural networks. It does not require any stochastic procedure and henceforth can be very fast. The generalized energy function of the network is first increased by reducing the voltage gain of each neuron. Then, the hardware annealing searches for the globally minimum energy state by continuously increasing the gain of neurons. The process of global optimization by the proposed hardware annealing method can be described by eigenvalues in the time-varying dynamic system.

AB - An engineering annealing method for optimal solutions of cellular neural networks is presented. Cellular neural networks, have great potential in solving many important scientific problems in signal processing and optimization by the use of pre-determined templates. Hardware annealing, which is a paralleled version of effective mean-field annealing in analog networks, is a highly efficient method of finding optimal solutions for cellular neural networks. It does not require any stochastic procedure and henceforth can be very fast. The generalized energy function of the network is first increased by reducing the voltage gain of each neuron. Then, the hardware annealing searches for the globally minimum energy state by continuously increasing the gain of neurons. The process of global optimization by the proposed hardware annealing method can be described by eigenvalues in the time-varying dynamic system.

UR - http://www.scopus.com/inward/record.url?scp=0028749129&partnerID=8YFLogxK

U2 - 10.1109/CNNA.1994.381666

DO - 10.1109/CNNA.1994.381666

M3 - Paper

AN - SCOPUS:0028749129

SP - 279

EP - 284

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 -

Optimal solutions of selected cellular neural network applications by the hardware annealing method

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this