Clustering of the self-organizing map
IEEE Transactions on Neural NetworksPublished 1 May 2000
Juha Vesanto, Esa Alhoniemi
Citations2,665
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The two-stage procedure--first using SOM to produce the prototypes that are then clustered in the second stage--is found to perform well when compared with direct clustering of the data and to reduce the computation time.
Abstract
The self-organizing map (SOM) is an excellent tool in exploratory phase of data mining. It projects input space on prototypes of a low-dimensional regular grid that can be effectively utilized to visualize and explore properties of the data. When the number of SOM units is large, to facilitate quantitative analysis of the map and the data, similar units need to be grouped, i.e., clustered. In this paper, different approaches to clustering of the SOM are considered. In particular, the use of hierarchical agglomerative clustering and partitive clustering using k-means are investigated. The two-stage procedure--first using SOM to produce the prototypes that are then clustered in the second stage--is found to perform well when compared with direct clustering of the data and to reduce the computation time.
Keywords
Computer Science
Springer series in information sciencesSelf-Organizing Maps
10,377 Citations1997Teuvo Kohonen
The mathematical preliminaries, background, basic ideas, and implications of the Self-Organising Map algorithm are expounded in a manner which is accessible without prior expert knowledge.
IEEE Transactions on Pattern Analysis and Machine IntelligenceA Cluster Separation Measure
8,543 Citations1979David L. Davies, Donald W. Bouldin
A measure is presented which indicates the similarity of clusters which are assumed to have a data density which is a decreasing function of distance from a vector characteristic of the cluster which can be used to infer the appropriateness of data partitions.
PsychometrikaMultidimensional Scaling by Optimizing Goodness of Fit to a Nonmetric Hypothesis
7,398 Citations1964Joseph B. Kruskal
The fundamental hypothesis is that dissimilarities and distances are monotonically related, and a quantitative, intuitively satisfying measure of goodness of fit is defined to this hypothesis.
PsychometrikaNonmetric Multidimensional Scaling: A Numerical Method
4,882 Citations1964Joseph B. Kruskal
The numerical methods required in the approach to multi-dimensional scaling are described and the rationale of this approach has appeared previously.
Neural ComputationFast Learning in Networks of Locally-Tuned Processing Units
4,219 Citations1989John Moody, Christian J. Darken
This work proposes a network architecture which uses a single internal layer of locally-tuned processing units to learn both classification tasks and real-valued function approximations (Moody and Darken 1988).
PsychometrikaAn Examination of Procedures for Determining the Number of Clusters in a Data Set
3,870 Citations1985Glenn W. Milligan, Martha C. Cooper
A Monte Carlo evaluation of 30 procedures for determining the number of clusters was conducted on artificial data sets which contained either 2, 3, 4, or 5 distinct nonoverlapping clusters to provide a variety of clustering solutions.
IEEE Transactions on ComputersA Nonlinear Mapping for Data Structure Analysis
3,381 Citations1969John W. Sammon
An algorithm for the analysis of multivariate data is presented along with some experimental results that is based upon a point mapping of N L-dimensional vectors from the L-space to a lower-dimensional space such that the inherent data "structure" is approximately preserved.
ComputerChameleon: hierarchical clustering using dynamic modeling
2,102 Citations1999George Karypis, Eui-Hong Han +1 more
Chameleon's key feature is that it accounts for both interconnectivity and closeness in identifying the most similar pair of clusters, which is important for dealing with highly variable clusters.
Queensland's institutional digital repository (The University of Queensland)Mixture models : inference and applications to clustering
2,074 Citations1988Geoffrey J. McLachlan, K. E. Basford
Data preparation for data mining
1,369 Citations1999Dorian Pyle
A twenty-five-year veteran of what has become the data mining industry, Pyle shares his own successful data preparation methodology, offering both a conceptual overview for managers and complete technical details for IT professionals.
IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)Some new indexes of cluster validity
1,142 Citations1998James C. Bezdek, Nikhil R. Pal
IEEE Transactions on Neural NetworksSelf organization of a massive document collection
911 Citations2000Teuvo Kohonen, Samuel Kaski +5 more
A system that is able to organize vast document collections according to textual similarities based on the self-organizing map (SOM) algorithm, based on 500-dimensional vectors of stochastic figures obtained as random projections of weighted word histograms.
IEEE Transactions on Information TheoryAsymptotically optimal block quantization
869 Citations1979A. Gersho
A heuristic argument generalizing Bennett's formula to block quantization where a vector of random variables is quantized is given, leading to a rigorous method for obtaining upper bounds on the minimum distortion for block quantizers.
IEEE Transactions on Neural NetworksCurvilinear component analysis: a self-organizing neural network for nonlinear mapping of data sets
651 Citations1997Pierre Demartines, J. Hérault
A self-organized neural network performing two tasks: vector quantization of the submanifold in the data set (input space) and nonlinear projection of these quantizing vectors toward an output space, providing a revealing unfolding of theSub manifold.
Physical Review LettersSuperparamagnetic Clustering of Data
544 Citations1996Marcelo Blatt, Shai Wiseman +1 more
This work presents a new approach for clustering, based on the physical properties of an inhomogeneous ferromagnetic model, which outperforms other algorithms for toy problems as well as for real data.
IEEE Transactions on Information TheoryAsymptotic quantization error of continuous signals and the quantization dimension
537 Citations1982P. Zádor
Extensions of the limiting qnanfizafion error formula of Bennet are proved and random quantization, optimal quantization in the presence of an output information constraint, and quantization noise in high dimensional spaces are investigated.
European Journal of Operational ResearchA comparison of SOM neural network and hierarchical clustering methods
352 Citations1996Paul Mangiameli, Shaw K. Chen +1 more
A Self Organizing Map (SOM) neural network clustering methodology is used and it is demonstrated that it is superior to the hierarchical clustering methods.
IEEE Transactions on Neural NetworksVariants of self-organizing maps
330 Citations1990Jari Kangas, Teuvo Kohonen +1 more
Neural Processing LettersGrowing Grid — a self-organizing network with constant neighborhood range and adaptation strength
324 Citations1995Bernd Fritzke
A novel self-organizing network which is generated by a growth process where both the neighborhood range used to co-adapt units in the vicinity of the winning unit and the adaptation strength are constant during the growth phase.
IEEE Transactions on Neural NetworksA nonlinear projection method based on Kohonen's topology preserving maps
242 Citations1995Martin A. Kraaijveld, Jianchang Mao +1 more
Experiments indicate that the performance of the Kohonen projection method is comparable or better than Sammon's method for the purpose of classifying clustered data.
Journal of Mathematical Imaging and VisionClustering properties of hierarchical self-organizing maps
192 Citations1992Jouko Lampinen, Erkki Oja
In experiments with both artificial and real data it is demonstrated that the multilayer SOM forms clusters that match better to the desired classes than do direct SOM's, classical k-means, or Isodata algorithms.
Clustering Properties of Hierarchical Self-Organizing Maps
179 Citations1993Jouko Lampinen, Erkki Oja
Elsevier eBooksSELF-ORGANIZING MAPS: OPHMIZATION APPROACHES
118 Citations1991Teuvo Kohonen
In this discussion, the Self-Organizing Map algorithm is related to the formalisms of stochastic approximation and optimization theory and derived of the optimal recursive formula for the basic Vector Quantization is included.
IEEE Transactions on Neural NetworksAsymptotic level density for a class of vector quantization processes
115 Citations1991Helge Ritter
It is shown that for a class of vector quantization processes, related to neural modeling, that the asymptotic density Q(x ) of the quantization levels in one dimension in terms of the input signal distribution P(x) is a power law C-P(x)(alpha), where the exponent alpha depends on the number n of neighbors on each side of a unit.
Pattern Recognition LettersInterpreting the Kohonen self-organizing feature map using contiguity-constrained clustering
115 Citations1995Fionn Murtagh
An interpretation phase is proposed, to complement usage of the Kohonen self-organizing feature map (SOFM) method, which segments the SOFM output, using an agglomerative contiguity-constrained clustering method.
Data Mining and Knowledge DiscoveryA Scalable Parallel Algorithm for Self-Organizing Maps with Applications to Sparse Data Mining Problems
101 Citations1999Richard D. Lawrence, George Almási +1 more
A scalable parallel implementation of the self organizing map (SOM) suitable for data-mining applications involving clustering or segmentation against large data sets such as those encountered in the analysis of customer spending patterns is described.
Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topicsPhase transitions in stochastic self-organizing maps
88 Citations1997Thore Graepel, Matthias Burger +1 more
Simulated annealing and codebook design
84 Citations2003J. Vaisey, A. Gersho
The application of simulated annealing to the design of a codebook for a vector quantizer (VQ) that is used to code images are studied and the mean-squared-error (MSE) is used as the distortion measure during the design.
CRC Press, Inc. eBooksIndustrial Applications of Neural Networks
73 Citations1998Lakhmi C. Jain, V. Rao Vemuri
From the Publisher: Industrial Applications of Neural Networks explores the success of neural networks in different areas of engineering endeavors and shows how the power of neural Networks can be exploited in modern engineering applications.
Neural ComputationComparison of SOM Point Densities Based on Different Criteria
69 Citations1999Teuvo Kohonen
The point density derived from the SOM algorithm turned out to be different from that minimizing the SOM distortion measure, showing that the model vectors produced by the basic SOM algorithm in general do not exactly coincide with the optimum of the distortion measure.
Neural ComputationComplexity Optimized Data Clustering by Competitive Neural Networks
69 Citations1993Joachim M. Buhmann, H. Kühnel
This work discusses a clustering strategy that explicitly reflects the tradeoff between simplicity and precision of a data representation, and establishes a unifying framework for different clustering methods like K-means clustering, fuzzy clusters, entropy constrained vector quantization, or topological feature maps and competitive neural networks.
WORLD SCIENTIFIC eBooksIndustrial Applications of Neural Networks
68 Citations1998Françoise Fogelman Soulié, Patrick Gallinari
This book is a collection of real-world applications of neural networks, which were presented at the ICANN '95 conference of the European Neural Network Society, and covers all major areas of industrial and service activities.
Self-organizing map as a new method for clustering and data analysis
55 Citations2005Xuegong Zhang, Yanda Li
An application of self-organizing maps as a method of clustering and data analysis, called SOM Analysis, which has some advantages over the traditional clustering algorithms in that it suits more general data distributions and needs less a priori knowledge.
Elsevier eBooksVisualizing High-Dimensional Structure with the Incremental Grid Growing Neural Network
51 Citations1995Justine Blackmore, Risto Miikkulainen
This paper proposes an algorithm that combines the topology-preserving characteristics of self-organizing maps with a flexible, adaptive structure that learns the cluster boundaries in the data.
International Conference on Acoustics, Speech, and Signal ProcessingVector quantization codebook generation using simulated annealing
46 Citations2003J. Kelly Flanagan, Darryl Morrell +3 more
Convergence of the algorithm to the globally optimal codebook in finite time is proved, and experimental results indicate that the proposed algorithm obtains the best known codebook for the experimental situation described by R.M. Gray and E.D. Karnin.
Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topicsSuperparamagnetic clustering of data
44 Citations1998Shai Wiseman, Marcelo Blatt +1 more
The physical aspects of a recently introduced method for data clustering, based on an inhomogeneous Potts model, are considered in detail and the spatial resolution of the clustering method is argued to be connected to the correlation length of spin fluctuations.
Coloring that reveals high-dimensional structures in data
35 Citations2003Samuel Kaski, Jarkko Venna +1 more
A method for assigning colors to displays of cluster structures of high-dimensional data, such that the perceptual differences of the colors reflect the distances in the original data space as faithfully as possible.
Improving the Learning Speed in Topological Maps of Patterns
32 Citations1990Joaquim Rodrigues, Luı́s B. Almeida
A method of improving the learning speed, by starting the map with very few units and increasing that number progressively until the map reaches its final size, which dramatically reduces the time needed for the “unfolding" phase and also yields some improvements in the asymptotic convergence phase.
Intelligent Data AnalysisInteractive interpretation of hierarchical clustering
26 Citations1998Eric Boudaillier, Georges Hébrail
A new interactive interface is proposed to help the user to interpret the result of such a clustering process, according to the item characteristics, and has been applied successfully to a special case of items providing nice graphical representations.
Clustering with competing self-organizing maps
21 Citations2003Yu Cheng
The discovery process for the number of clusters is studied and compared to k-means clustering, and the frequency of a clusters outcome is used as a measure of the validity of the clustering.
International Conference on Artificial Neural NetworksHierarchical self-organising networks
19 Citations1989S.P. Luttrell
It is demonstrated how hierarchical self-organising neural networks may be constructed by further application of the robust hidden layer principle.