# Show Reference: "Varying Cooperation in {SOM} for Improved Function Approximation"

Varying Cooperation in SOM for Improved Function Approximation In IEEE International Conference on Neural Networks, Vol. 1 (June 1996), pp. 1-6 vol.1, doi:10.1109/icnn.1996.548857 by Josef Göppert, Wolfgang Rosenstiel
@inproceedings{goeppert-and-rosenstiel-1996,
abstract = {This paper presents a data-driven principle for the adaptation of
the neighbourhood range in self-organizing maps ({SOM}). The objective is
a reduction of the approximation error in a counterpropagation-like
architecture. Therefore the neighbourhood cooperation range of neurons
in different regions of the training data space is adapted. In this
framework a neuron specific approximation error serves as a criterion.
Different examples show the influence of this modification onto the
training of the map and on the function approximation quality of the
output layer. This principle may also be used for other methods such as
the interpolated self-organizing map, the local linear maps and as input
quantizer for the radial basis function nets},
author = {G\"{o}ppert, Josef and Rosenstiel, Wolfgang},
booktitle = {IEEE International Conference on Neural Networks},
doi = {10.1109/icnn.1996.548857},
institution = {University of T\"{u}bingen},
isbn = {0-7803-3210-5},
keywords = {ann, learning, som},
month = jun,
pages = {1--6 vol.1},
posted-at = {2011-12-12 11:08:38},
priority = {2},
publisher = {IEEE},
title = {Varying Cooperation in {SOM} for Improved Function Approximation},
url = {http://dx.doi.org/10.1109/icnn.1996.548857},
volume = {1},
year = {1996}
}