Timo Honkela
ABSTRACT
Kohonen's Self-organizing Map (SOM) is a means for automatically arranging high-dimensional statistical data. The map attempts to represent all the input with optimal accuracy using a restricted set of models or prototypes. The prototypes also become ordered on the map grid so that similar prototypes are close to each other and dissimilar prototypes far from each other. The SOM is useful in clustering, abstraction, and visualization through dimensionality reduction. It has been used in a multitude of application areas ranging form speech recognition to data mining of tests and form robotics to process monitoring. The unsupervised learning scheme of the SOM makes it well suited for applications in which the input data cannot be labeled. A map is ordered and it follows the patterns of the input data in a non-linear but generalizing fashion. All this makes it well suited for data analysis and many areas in developing intelligent systems. In this article, the general principles of using the SOM in data analysis are considered reflecting on the concept of context. An illustrative experiment of data analysis is presented.
- A.T. Beck and R.A. Steer. Screening for adolescent depression: A comparison of depression scales. Journal of the American Academy of Child and Adolescent Psychiatry, 30(1):58-66.Google Scholar
- M. Berthold and D.J. Hand (eds). Intelligent Data Analysis; An Introduction. Springer, 1999. Google ScholarDigital Library
- T. Honkela, V. Pulkki, and T. Kohonen. Contextual relations of words in Grimm tales analyzed by self-organizing map. Proceedings of ICANN-95, International Conference on Artificial Neural Networks, F. Fogelman-Souli and P. Gallinari (eds), vol. 2, EC2 et Cie, Paris, pp. 3-7, 1995.Google Scholar
- T. Honkela, S. Kaski, K. Lagus, and T. Kohonen. Newsgroup exploration with WEBSOM method and browsing interface. Technical Report A32, Helsinki University of Technology, Laboratory of Computer and Information Science, Espoo, Finland, January, 1996.Google Scholar
- T. Honkela. Self-Organizing Maps in Natural Language Processing. PhD Thesis, Helsinki University of Technology, Espoo, Finland, 1997. See http://www.cis.hut.fi/r4ho/thesis/Google Scholar
- H. Hrmann. Meaning and Context. Plenum Press, New York, 1986.Google ScholarCross Ref
- G.R. Iversen. Contextual analysis. Newbury Park, Calif. Sage, 1991.Google Scholar
- S. Karvonen and O. Rahkonen. Cultural variation in lifestyle and health-related behavior among young people (in Finnish). Yhteiskun-tapolitiikka (in print), 2000.Google Scholar
- S. Kaski. Data exploration using self-organizing maps. Acta Polytechnica Scandinavica, Mathematics, Computing and Management in Engineering Series No. 82. DTech Thesis, Helsinki University of Technology, Finland, 1997.Google Scholar
- S. Kaski and T. Kohonen. Exploratory data analysis by the selforganizing map: Structures of welfare and poverty in the world. Neural Networks in Financial Engineering. Proceedings of the Third International Conference on Neural Networks in the Capital Markets, London, England, 11-13 October, 1995, World Scientific, Singapore, pp. 498-507, 1996.Google Scholar
- S. Kaski, T. Honkela, K. Lagus, and T. Kohonen. WEBSOM -Selforganizing maps of document collections, Neurocomputing, 21:101-117, 1998.Google ScholarCross Ref
- T. Kohonen. Self-organizing formation of topologically correct feature maps. Biological Cybernetics, 43(1):59-69, 1982.Google ScholarCross Ref
- T. Kohonen. Self-Organizing Maps. Springer, Berlin, Heidelberg, 1995. (Second, extended edition 1997) Google ScholarDigital Library
- T. Kohonen, S. Kaski, K. Lagus, J. Salojrvi, J. Honkela, V. Paatero, and A. Saarela. Self organization of a massive text document collection E. Oja and S. Kaski (eds.), Kohoner& Maps, Elsevier, Amsterdam, pp. 171-182, 1999.Google ScholarCross Ref
- J.L. Kolodner. Case-Based Reasoning. Morgan Kaufmann, 1993. Google ScholarDigital Library
- X. Lin, D. Soergel, and G. Marchionini. A self-organizing semantic map for information retrieval. In Proceedings of 14th. Ann. International ACM/SIGIR Conference on Research & Development in Information Retrieval, pp. 262-269, 1991. Google ScholarDigital Library
- H. Ritter and T. Kohonen. Self-organizing semantic maps. Biological Cybernetics, 61(4):241-254, 1989.Google ScholarDigital Library
- J. Vesanto and J. Ahola. Hunting for correlations in data using the self-organizing map. Proceedings of CIMA '99, International ICSC Congress on Computational Intelligence. H. Bothe, E. Oja, E. Massad, and C. Haefke (eds.), ICSC Academic Press, pp. 279-285, 1999.Google Scholar
Index Terms
- Kohonen's self-organizing maps in contextual analysis of data
Recommendations
Essentials of the self-organizing map
The self-organizing map (SOM) is an automatic data-analysis method. It is widely applied to clustering problems and data exploration in industry, finance, natural sciences, and linguistics. The most extensive applications, exemplified in this paper, can ...
Kohonen's self-organizing maps in contextual analysis of data
Information organization and databasesSelf-organizing neural projections
2006 Special issue: Advances in self-organizing maps--WSOM'05The Self-Organizing Map (SOM) algorithm was developed for the creation of abstract-feature maps. It has been accepted widely as a data-mining tool, and the principle underlying it may also explain how the feature maps of the brain are formed. However, ...
Comments