'Neural-gas' network for vector quantization and its application to time-series prediction
- 1 July 1993
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 4 (4), 558-569
- https://doi.org/10.1109/72.238311
Abstract
A neural network algorithm based on a soft-max adaptation rule is presented. This algorithm exhibits good performance in reaching the optimum minimization of a cost function for vector quantization data compression. The soft-max rule employed is an extension of the standard K-means clustering procedure and takes into account a neighborhood ranking of the reference (weight) vectors. It is shown that the dynamics of the reference (weight) vectors during the input-driven adaptation procedure are determined by the gradient of an energy function whose shape can be modulated through a neighborhood determining parameter and resemble the dynamics of Brownian particles moving in a potential determined by the data point density. The network is used to represent the attractor of the Mackey-Glass equation and to predict the Mackey-Glass time series, with additional local linear mappings for generating output values. The results obtained for the time-series prediction compare favorably with the results achieved by backpropagation and radial basis function networks.Keywords
This publication has 24 references indexed in Scilit:
- Statistical mechanics and phase transitions in clusteringPhysical Review Letters, 1990
- Nonlinear forecasting as a way of distinguishing chaos from measurement error in time seriesNature, 1990
- Three-dimensional neural net for learning visuomotor coordination of a robot armIEEE Transactions on Neural Networks, 1990
- Nonlinear prediction with self-organizing mapsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990
- Topology-conserving maps for learning visuo-motor-coordinationNeural Networks, 1989
- Convergence properties of Kohonen's topology conserving maps: fluctuations, stability, and dimension selectionBiological Cybernetics, 1988
- Image coding using vector quantization: a reviewIEEE Transactions on Communications, 1988
- Vector quantization of images based upon the Kohonen self-organizing feature mapsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1988
- Vector quantization in speech codingProceedings of the IEEE, 1985
- Oscillation and Chaos in Physiological Control SystemsScience, 1977