Self-Organizing Maps
- 1 January 1998
- journal article
- research article
- Published by Taylor & Francis Ltd in Substance Use & Misuse
- Vol. 33 (2), 365-381
- https://doi.org/10.3109/10826089809115871
Abstract
The self-organizing map is a statistical data analysis method of the branch of unsupervised learning, whose goal is to determine the properties of input data without explicit feedback from a teacher. Originally inspired by feature maps in sensory systems, it has greatly contributed to our understanding of self-organization in the brain in general and the development of feature maps in particular. Through interplay of lateral inhibition and Hebbian learning within a localized region of a one-layered neural network, the network acquires a low-dimensional representation of high-dimensional input features, which respects topological relationships of the input space.Keywords
This publication has 18 references indexed in Scilit:
- Putative strategies of scene segmentation in monkey visual cortexNeural Networks, 1994
- Quantifying the neighborhood preservation of self-organizing feature mapsIEEE Transactions on Neural Networks, 1992
- Statistical-mechanical analysis of self-organization and pattern formation during the development of visual mapsPhysical Review A, 1992
- Self-organizing maps: stationary states, metastability and convergence rateBiological Cybernetics, 1992
- A neural network architecture for figure-ground separation of connected scenic figuresNeural Networks, 1991
- Asymptotic level density for a class of vector quantization processesIEEE Transactions on Neural Networks, 1991
- Self-organizing semantic mapsBiological Cybernetics, 1989
- Self-organized formation of topologically correct feature mapsBiological Cybernetics, 1982
- How patterned neural connections can be set up by self-organizationProceedings of the Royal Society of London. B. Biological Sciences, 1976
- A model of visuomotor mechanisms in the frog optic tectumMathematical Biosciences, 1976