Boltzmann learning of parameters in cellular neural networks

Lars Kai Hansen

doi:10.1109/CNNA.1992.274354

Boltzmann learning of parameters in cellular neural networks

Lars Kai Hansen

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

552 Downloads (Pure)

Abstract

The use of Bayesian methods to design cellular neural networks for signal processing tasks and the Boltzmann machine learning rule for parameter estimation is discussed. The learning rule can be used for models with hidden units, or for completely unsupervised learning. The latter is exemplified by unsupervised adaptation of an image segmentation cellular network. The learning rule is applied to adaptive segmentation of satellite imagery

Original language	English
Title of host publication	Proceedings of the 2nd Second International Workshop on Cellular Neural Networks and their Applications
Publisher	IEEE
Publication date	1992
Pages	62-67
ISBN (Print)	07-80-30875-1
DOIs	https://doi.org/10.1109/CNNA.1992.274354
Publication status	Published - 1992
Event	International Workshop on Cellular Neural Networks and their Applications - Munich, Germany Duration: 1 Jan 1992 → … Conference number: 2nd

Conference

Conference	International Workshop on Cellular Neural Networks and their Applications
Number	2nd
City	Munich, Germany
Period	01/01/1992 → …

Bibliographical note

Copyright: 1992 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE

Access to Document

10.1109/CNNA.1992.274354

KaiFinal published version, 297 KB

OpenUrl availability

Full text

Cite this

@inproceedings{3f9bc5dbbbad407c8b7eec585d73b005,

title = "Boltzmann learning of parameters in cellular neural networks",

abstract = "The use of Bayesian methods to design cellular neural networks for signal processing tasks and the Boltzmann machine learning rule for parameter estimation is discussed. The learning rule can be used for models with hidden units, or for completely unsupervised learning. The latter is exemplified by unsupervised adaptation of an image segmentation cellular network. The learning rule is applied to adaptive segmentation of satellite imagery",

author = "Hansen, {Lars Kai}",

note = "Copyright: 1992 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE; International Workshop on Cellular Neural Networks and their Applications, CNNA-92 ; Conference date: 01-01-1992",

year = "1992",

doi = "10.1109/CNNA.1992.274354",

language = "English",

isbn = "07-80-30875-1",

pages = "62--67",

booktitle = "Proceedings of the 2nd Second International Workshop on Cellular Neural Networks and their Applications",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - Boltzmann learning of parameters in cellular neural networks

AU - Hansen, Lars Kai

N1 - Conference code: 2nd

PY - 1992

Y1 - 1992

N2 - The use of Bayesian methods to design cellular neural networks for signal processing tasks and the Boltzmann machine learning rule for parameter estimation is discussed. The learning rule can be used for models with hidden units, or for completely unsupervised learning. The latter is exemplified by unsupervised adaptation of an image segmentation cellular network. The learning rule is applied to adaptive segmentation of satellite imagery

AB - The use of Bayesian methods to design cellular neural networks for signal processing tasks and the Boltzmann machine learning rule for parameter estimation is discussed. The learning rule can be used for models with hidden units, or for completely unsupervised learning. The latter is exemplified by unsupervised adaptation of an image segmentation cellular network. The learning rule is applied to adaptive segmentation of satellite imagery

U2 - 10.1109/CNNA.1992.274354

DO - 10.1109/CNNA.1992.274354

M3 - Article in proceedings

SN - 07-80-30875-1

SP - 62

EP - 67

BT - Proceedings of the 2nd Second International Workshop on Cellular Neural Networks and their Applications

PB - IEEE

T2 - International Workshop on Cellular Neural Networks and their Applications

Y2 - 1 January 1992

ER -

Boltzmann learning of parameters in cellular neural networks

Abstract

Conference

Bibliographical note

Access to Document

OpenUrl availability

Fingerprint

Cite this