1994 Special Issue: Winner-take-all networks for physiological models of competitive learning
Neural Networks - Special issue: models of neurodynamics and behavior
Self-organizing maps
The Handbook of Brain Theory and Neural Networks
The Handbook of Brain Theory and Neural Networks
Asymptotic level density in topological feature maps
IEEE Transactions on Neural Networks
Homeostatic synaptic scaling in self-organizing maps
Neural Networks - 2006 Special issue: Advances in self-organizing maps--WSOM'05
Online estimation of electric arc furnace tap temperature by using fuzzy neural networks
Engineering Applications of Artificial Intelligence
Sleeping our way to weight normalization and stable learning
Neural Computation
Self-organizing maps with refractory period
ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
Assessing and classifying risk of pipeline third-party interference based on fault tree and SOM
Engineering Applications of Artificial Intelligence
Expert Systems: The Journal of Knowledge Engineering
Essentials of the self-organizing map
Neural Networks
| Hi-index | 0.00 |
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.