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

Jon Atli Benediktsson; Jan Larsen; Johannes R. Sveinsson; L. K. Hansen

doi:10.1117/12.331874

4 December 1998 Optimized combination, regularization, and pruning in parallel consensual neural networks

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

Proceedings Volume 3500, Image and Signal Processing for Remote Sensing IV; (1998) https://doi.org/10.1117/12.331874
Event: Remote Sensing, 1998, Barcelona, Spain

Abstract

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.

Citation Download Citation

Jon Atli Benediktsson, Jan Larsen, Johannes R. Sveinsson, and L. K. Hansen "Optimized combination, regularization, and pruning in parallel consensual neural networks", Proc. SPIE 3500, Image and Signal Processing for Remote Sensing IV, (4 December 1998); https://doi.org/10.1117/12.331874

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available