Abstract
At the University of Linz a remarkable associative memory model has been developed. A neural network analogous self learning system with the capability of parallel and serial association. But, for data mining tasks it has one shortcoming. It can not reproduce how often it has seen a part of a pattern in its past — it is not able to compute frequencies. In this contribution we introduce an extension of the model with which frequencies, support and confidence are feasible. Besides, all advantages of the model could be retained. Short examples and a comparison with a common data mining tool complete the paper.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
R. Agrawal, et al.: Fast discovery of association rules. In: Agrawal, H. Mannila R. Srikant, H. Toivonnen, I. Verkamo (eds.): Advances in Knowledge Discovery and Data Mining, AAAI Press / The MIT Press, 1996 pp. 307–328
P. Andlinger: Fuzzy Neunet. Dissertation, Universität Linz 1992
S. Burgholzer: Entwurf und Realisierung einer allgemeinen Experimentierumgebung für Neuronale Netze und Implementierung der neuronalen Netze Fuzzy Neunet, Fuzzy Neunet S und Error Backpropagation. Diploma Thesis, Universität Linz 1996
L. Dale, T. Bench-Capon: A Datamining Tool for Producing Characteristic Classifications in Legal Domain. In: A. Hameurlain, A Min Tjoa (eds.): Database and Expert Systems Application, Springer 1997, pp.186–191
DBMiner E1.0 (Beta), User Manual For Windows NT, Data Mining Research Group, Intelligent Database Systems Research Laboratory, School of Computing Science, Simon Fraser University, British Columbia, Canada V5A 1S6
U.M. Fayyad, G. Piatetsky-Shapiro, P. Smyth und R. Uthurusamy: The KDD process for extracting useful knowledge from volumes of data. Communications of the ACM, November 1996, Vol. 39, No. 11. pp. 27–34
U.M. Fayyad et al.: From Datamining to Knowledge Discovery: An overview. In: U.M. Fayyad, G. Piatetsky-Shapiro, P. Smyth und R. Uthurusamy (eds.): Advances in Knowledge Discovery and Data Mining”, AAAI Press / The MIT Press, 1996. pp. 1–34
H. Hagmüller: Entwurf und Implementierung einer Simulationsumgebung für neuronennetzanaloge Modelle und Implementierung der neuronalen Netze Neunet 3, Neunet 3S und Perzeptron. Diploma Thesis, Universität Linz 1996
F. Lehner: Erkennen von Ähnlichkeiten im System Neunet. Diploma Thesis, Universität Linz 1984
H. Lu, R. Setiono, H. Liu: Effective Data Mining Using Neural Networks. IEEE Transactions on Knowledge and Data Engineering, Vol. 8, No. 6, December 1996 pp.957–961
E.R. Reichl: Lernende Systeme. Informatikberichte, Universität Linz 1975
E.R. Reichl: Neuronennetz-ähnliche Strukturen als Assoziativspeicher. Applied Computer Science, Bd.8: Datenstrukturen, Graphen, Algorithmen 1978
E.R. Reichl: Computermodelle zum menschlichen Gedächtnis. Schriftenreihe der Österreichischen Computergesellschaft, Bd.15: Informatik und Psychologie, 1982
F.D. Valach: Parallelen in Struktur und Eigenschaften zwischen einem Assoziativspeichermodell und dem Zentralnervensystem. Dissertation, Universität Linz 1984
Y. Show-Jane, A.L.P. Chen: An Efficient Datamining Technique for Discovery Interesting Association Rules. In: A. Hameurlain, A Min Tjoa (eds.): Database and Expert Systems Application, Springer 1997, pp. 664–669
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Küng, J., Sylvia, H., Horst, H. (1999). Knowledge Discovery with the Associative Memory Modell Neunet. In: Bench-Capon, T.J., Soda, G., Tjoa, A.M. (eds) Database and Expert Systems Applications. DEXA 1999. Lecture Notes in Computer Science, vol 1677. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48309-8_13
Download citation
DOI: https://doi.org/10.1007/3-540-48309-8_13
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66448-2
Online ISBN: 978-3-540-48309-0
eBook Packages: Springer Book Archive