Optimized combination, regularization, and pruning in parallel consensual neural networks

Jon A. Benediktsson*, Jan Larsen, Johannes R. Sveinsson, L. K. Hansen

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)


Optimized combination, regularization, and pruning is proposed for the Parallel Consensual Neural Networks (PC-NNs) which is a neural network architecture based on the consensus of a collection of stage neural networks trained on the same input data with different representations. Here, a regularization scheme is presented for the PCNN and in training a regularized cost function is minimized. The use of this regularization scheme in conjunction with Optimal Brain Damage pruning is suggested both to optimize the architecture of the individual stage networks and to avoid overfitting. Experiments are conducted on a multisource remote sensing and geographic data set consisting of six data source. The results obtained by the proposed version of PCNN are compared to other classification approaches such as the original PCNN, single stage neural networks and statistical classifiers. In comparison to the originally proposed PCNNs, the use of pruning and regularization not only produces simpler PCNNs but also gives higher classification accuracies. In particular, using the proposed approach, a neural network based non-linear combination scheme, for the individual stages in the PCNN, produces excellent overall classification accuracies for both training and test data.

Original languageEnglish
Title of host publicationImage and Signal Processing for Remote Sensing IV
EditorsSebastiano Bruno Serpico
Number of pages11
ISBN (Electronic)9780819429599
Publication statusPublished - 4 Dec 1998
EventImage and Signal Processing for Remote Sensing IV 1998 - Barcelona, Spain
Duration: 21 Sep 199825 Sep 1998

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X


ConferenceImage and Signal Processing for Remote Sensing IV 1998

Bibliographical note

Funding Information:
Technical University (DTTJ), Lyngby, Denmark. The research is in part supported by the Icelandic Research Council and the Research Fund of the University of Iceland. The Anderson River SAR/MSS data set was acquired, preprocessed, and loaned by the Canada Centre for Remote Sensing, Department of Energy Mines, and Resources, of the Government of Canada.

Publisher Copyright:
© 1998 SPIE.

Other keywords

  • Consensus Theory
  • Data Fusion
  • Neural Networks
  • Regularization
  • Remote Sensing


Dive into the research topics of 'Optimized combination, regularization, and pruning in parallel consensual neural networks'. Together they form a unique fingerprint.

Cite this