A Topographic Product for the Optimization of Self-Organizing Feature Maps
Abstract
Optimizing the performance of self-organizing feature maps like the Ko(cid:173) honen map involves the choice of the output space topology. We present a topographic product which measures the preservation of neighborhood relations as a criterion to optimize the output space topology of the map with regard to the global dimensionality DA as well as to the dimensi(cid:173) ons in the individual directions. We test the topographic product method not only on synthetic mapping examples, but also on speech data. In the latter application our method suggests an output space dimensionality of DA = 3, in coincidence with recent recognition results on the same data set.
Cite
Text
Bauer et al. "A Topographic Product for the Optimization of Self-Organizing Feature Maps." Neural Information Processing Systems, 1991.Markdown
[Bauer et al. "A Topographic Product for the Optimization of Self-Organizing Feature Maps." Neural Information Processing Systems, 1991.](https://mlanthology.org/neurips/1991/bauer1991neurips-topographic/)BibTeX
@inproceedings{bauer1991neurips-topographic,
title = {{A Topographic Product for the Optimization of Self-Organizing Feature Maps}},
author = {Bauer, Hans-Ulrich and Pawelzik, Klaus and Geisel, Theo},
booktitle = {Neural Information Processing Systems},
year = {1991},
pages = {1141-1147},
url = {https://mlanthology.org/neurips/1991/bauer1991neurips-topographic/}
}