Högskolan i Skövde

his.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • apa-cv
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Radar Image Segmentation using Self-Adapting Recurrent Networks
University of Skövde, Department of Computer Science. (The Connectionist Research Group)ORCID iD: 0000-0001-6883-2450
1997 (English)Report (Other academic)
Abstract [en]

This paper presents a novel approach to the segmentation and integration of (radar) images using a second-order recurrent artificial neural network architecture consisting of two sub- networks: a function network that classifies radar measurements into four different categories of objects in sea environments (water, oil spills, land and boats), and a context network that dynamically computes the function network's input weights. It is shown that in experiments (using simulated radar images) this mechanism outperforms conventional artificial neural networks since it allows the network to learn to solve the task through a dynamic adaptation of its classification function based on its internal state closely reflecting the current context.

Abstract [en]

HS-IDA-TR-97-002

Annotation:

International Conference on Engineering Applications of Neural Networks (EANN 96)

In International Journal of Neural Systems, 8(1), 47-54. Feb 1997

Place, publisher, year, edition, pages
Skövde: University of Skövde , 1997.
Series
IDA Technical Reports ; HS-IDA-TR-97-002
Keywords [en]
radar image segmentation, recurrent artificial neural networks, second-order networks, self-adaptation, target classification
National Category
Information Systems
Identifiers
URN: urn:nbn:se:his:diva-1238OAI: oai:DiVA.org:his-1238DiVA, id: diva2:2371
Available from: 2008-06-17 Created: 2008-06-17 Last updated: 2021-05-20Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Fulltext

Authority records

Ziemke, Tom

Search in DiVA

By author/editor
Ziemke, Tom
By organisation
Department of Computer Science
Information Systems

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 242 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • apa-cv
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf