S-mAP: A Network with a Simple Self-Organization Algorithm for Generative Topographic Mappings
Abstract
The S-Map is a network with a simple learning algorithm that com(cid:173) bines the self-organization capability of the Self-Organizing Map (SOM) and the probabilistic interpretability of the Generative To(cid:173) pographic Mapping (GTM). The simulations suggest that the S(cid:173) Map algorithm has a stronger tendency to self-organize from ran(cid:173) dom initial configuration than the GTM. The S-Map algorithm can be further simplified to employ pure Hebbian learning, with(cid:173) out changing the qualitative behaviour of the network.
Cite
Text
Kiviluoto and Oja. "S-mAP: A Network with a Simple Self-Organization Algorithm for Generative Topographic Mappings." Neural Information Processing Systems, 1997.Markdown
[Kiviluoto and Oja. "S-mAP: A Network with a Simple Self-Organization Algorithm for Generative Topographic Mappings." Neural Information Processing Systems, 1997.](https://mlanthology.org/neurips/1997/kiviluoto1997neurips-smap/)BibTeX
@inproceedings{kiviluoto1997neurips-smap,
title = {{S-mAP: A Network with a Simple Self-Organization Algorithm for Generative Topographic Mappings}},
author = {Kiviluoto, Kimmo and Oja, Erkki},
booktitle = {Neural Information Processing Systems},
year = {1997},
pages = {549-555},
url = {https://mlanthology.org/neurips/1997/kiviluoto1997neurips-smap/}
}