Self-organizing neural projections - PubMed (original) (raw)
. 2006 Jul-Aug;19(6-7):723-33.
doi: 10.1016/j.neunet.2006.05.001. Epub 2006 Jun 12.
Affiliations
- PMID: 16774731
- DOI: 10.1016/j.neunet.2006.05.001
Self-organizing neural projections
Teuvo Kohonen. Neural Netw. 2006 Jul-Aug.
Abstract
The Self-Organizing Map (SOM) algorithm was developed for the creation of abstract-feature maps. It has been accepted widely as a data-mining tool, and the principle underlying it may also explain how the feature maps of the brain are formed. However, it is not correct to use this algorithm for a model of pointwise neural projections such as the somatotopic maps or the maps of the visual field, first of all, because the SOM does not transfer signal patterns: the winner-take-all function at its output only defines a singular response. Neither can the original SOM produce superimposed responses to superimposed stimulus patterns. This presentation introduces a new self-organizing system model related to the SOM that has a linear transfer function for patterns and combinations of patterns all the time. Starting from a randomly interconnected pair of neural layers, and using random mixtures of patterns for training, it creates a pointwise-ordered projection from the input layer to the output layer. If the input layer consists of feature detectors, the output layer forms a feature map of the inputs.
MeSH terms
LinkOut - more resources
Full Text Sources
Other Literature Sources