The growing neural gas and clustering of large amounts of data

Authors:
S. V. Mitsyn;G. A. Ososkov
Affiliations:
Joint Institute for Nuclear Research (JINR), Dubna, Moscow region, Russia;Joint Institute for Nuclear Research (JINR), Dubna, Moscow region, Russia
Venue:
Optical Memory and Neural Networks
Year:
2011

Citing 5
Cited 1

Applications of weighted Voronoi diagrams and randomization to variance-based k-clustering: (extended abstract)

SCG '94 Proceedings of the tenth annual symposium on Computational geometry
Pattern Recognition with Fuzzy Objective Function Algorithms

Pattern Recognition with Fuzzy Objective Function Algorithms
Self-Organizing Maps

Self-Organizing Maps
k-means++: the advantages of careful seeding

SODA '07 Proceedings of the eighteenth annual ACM-SIAM symposium on Discrete algorithms
NP-hardness of Euclidean sum-of-squares clustering

Machine Learning

FGNG: A fast multi-dimensional growing neural gas implementation

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The paper gives a brief consideration of a new approach to clustering of large amounts of data. Developed by the authors in the course of research into clustering of geographic and graphical data, the approach involves two-stage clustering. In the first stage we prepare the data by using an advanced algorithm of the growing neural gas to cluster the objects in the Voronoi regions with the aid of neural nets. In the second stage the reference vectors of the Voronoi regions are regarded as separate objects to permit the use of conventional complex methods of clustering. The paper offers a brief theoretical ground of this clustering algorithm and recommendations for choosing suitable neural-net methods. Simulated and air-photography data are used to exemplify the approach applications.