Summary
A two-level representation is proposed for huge and highly dimensional data sets: 1) a global and synthetic mapping of the topics issued from the data, and 2) a set of local axes, one per topic, ranking both the descriptors and the described objects. Two algorithms are presented for deriving these axes: the axial k-means results in strict clusters, each one being characterized with an ”axoïd”, or first component of a simplified ”spherical” factor analysis applied to this cluster. The local components analysis results in fuzzy, overlapping clusters, issued from the local maxima of a ”partial inertia” landscape, and which constitute an absolute optimum. Interesting properties of these methods are presented and argued: graded, progressive type of representation connected to human categorization schemes; distributional equivalence in the space of the objects; stable local representations; computer efficiency.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
BEZDEK, J.C. (1974): Numerical taxonomy with fuzzy sets. Journal of Mathematical Biology, vol. 1, 57–71
BENZECRJ, J.P. (1969): Approximation stochastique dans une algbre non norme commutative. Bull. Soc. Math. France, N 97, 225–241
DOMENGES, D., VOLLE, M. (1979): Analyse factorielle sphrique: une exploration. Annales de Rinsee, N35, 3–84.
ESCOFIER, B. (1978): Analyses factorielles et distances rpondant au critre d’quivalence distributionnelle, Revue de Stat. Applique, vol. 26, N4, 29–37.
ESCOUFIER, Y. (1988): Beyond correspondence analysis . In: H.H. Bock ed:. Classification and Related Methods of Data Analysis, Elsevier, Amsterdam, 505–514.
FORGY, E. (1965): Cluster analysis of multivariate data: efficiency vs. interpretability of classifications, Abstract, Biometrics, vol. 21, 768–769.
FURNAS, G.W., LANDAUER, T.K., DUMAIS, S., GOMEZ, L.M. (1983): Statistical semantics: Analysis of the potential performance of key-word information systems. Bell System Technical Journal, vol.62, N6, 1753–1806.
LEBART, L. (1974): On the Benzecri’s method for finding eigenvectors through stochastic approximation. COMPSTAT Proc, Physica Verlag, Vienne, 202–211.
LELU, A., FRANCOIS C. (1992): Automatic generation of hypertext links in information retrieval systems. In: ECHT’92, ACM Press, New York, 112–121.
LELU, A. (1993): Modles neuronaux et incrmentaux pour l’analyse de flux de donnes documentaires et textuelles. Ph. D. dissertation, Universit Paris VI, Paris.
MAC QUEEN, J. (1967): Some methods for Classification and Analysis of Multivariate Observations. In: Proc. 5th Berkeley Symp. Math. Stat. Proba., 281–297.
OJA, E. (1982): A Simplified Neuron Model as a Principal Component Analyzer. Journal of Mathematical Biology, vol.15, 267–273
ROSENBLATT, D., LELU, A., GEORGEL, A. (1989): Learning in a single pass: A neural model for instantaneous principal component analysis and linear regression. In Proc. of the 1st IEE Conference on Neural Computing, London, 252–256.
ROSH, E., MERVIS, C. (1975): Family resemblances: studies in the internal structures of categories. Cognitive Psychology, vol. 6, 573–605.
THURSTONE L.L. (1947): Multiple-factor analysis. University of Chicago Press, Chicago
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lelu, A. (1994). Clusters and factors: neural algorithms for a novel representation of huge and highly multidimensional data sets. In: Diday, E., Lechevallier, Y., Schader, M., Bertrand, P., Burtschy, B. (eds) New Approaches in Classification and Data Analysis. Studies in Classification, Data Analysis, and Knowledge Organization. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-51175-2_27
Download citation
DOI: https://doi.org/10.1007/978-3-642-51175-2_27
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-58425-4
Online ISBN: 978-3-642-51175-2
eBook Packages: Springer Book Archive