Engineering applications of the self-organizing map
- 1 October 1996
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Proceedings of the IEEE
- Vol. 84 (10) , 1358-1384
- https://doi.org/10.1109/5.537105
Abstract
The self-organizing map (SOM) method is a new, powerful software tool for the visualization of high-dimensional data. It converts complex, nonlinear statistical relationships between high-dimensional data into simple geometric relationships on a low-dimensional display. As it thereby compresses information while preserving the most important topological and metric relationships of the primary data elements on the display, it may also be thought to produce some kind of abstractions. The term self-organizing map signifies a class of mappings defined by error-theoretic considerations. In practice they result in certain unsupervised, competitive learning processes, computed by simple-looking SOM algorithms. Many industries have found the SOM-based software tools useful. The most important property of the SOM, orderliness of the input-output mapping, can be utilized for many tasks: reduction of the amount of training data, speeding up learning nonlinear interpolation and extrapolation, generalization, and effective compression of information for its transmission.Keywords
This publication has 119 references indexed in Scilit:
- Self-organizing feature maps and their application to digital coding of informationPublished by Springer Nature ,2006
- Convergence behaviour of connectionist models in large scale diagnostic problemsPublished by Springer Nature ,2005
- Analysing particle jets with artificial neural networksPublished by Springer Nature ,2005
- A systematic method for rational definition of plant diagnostic symptoms by self-organizing neural networksNeurocomputing, 1996
- Distortion tolerant pattern recognition based on self-organizing feature extractionIEEE Transactions on Neural Networks, 1995
- Power system static security assessment using the Kohonen neural network classifierIEEE Transactions on Power Systems, 1992
- An artificial neural-net based technique for power system dynamic stability with the Kohonen modelIEEE Transactions on Power Systems, 1992
- Neural networks for power systems alarm handlingNeurocomputing, 1992
- Derivation of a class of training algorithmsIEEE Transactions on Neural Networks, 1990
- Cell placement by self-organisationNeural Networks, 1990