Abstract
The paper deals with Acyclic Graph Data Structures (AGDS) and with model of a self-organizing map (SOM) that has been modified for processing of AGDS. The motivation was found in the real world of the Academic Information System (AIS) at P. J. Šafárik University in Košice. To the modified SOM Neural Network (SOM NN), there are added contexts and counters which are built in a training phase of the neural network. The trained SOM NN in active phase can compute more information which is used to built an answer to some questions. The working application was tested on the study programs in informatics, the test results are very closed to the real values.
Supported by the Slovak Scientific Grant Agency VEGA, Grant No. 1/0035/09.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Frasconi, P.M., Gori, M., Sperduti, A.: A general framework of adaptive processing of data structures. IEEE-NN 9(5), 768–786 (1998)
Hagenbuchner, M., Sperduti, A., Tsoi, A.C.: A self-organizing map for adaptive processing of structured data. IEEE Transactions on Neural Networks 14(3), 491–505 (2003)
Hagenbuchner, M., Tsoi, A.C.: A supervised self-organizing map for structures. In: Proceedings IEEE International Joint Conference on Neural Networks, vol. 3, pp. 1923–1928. IEEE, Los Alamitos (2004)
Hagenbuchner, M., Tsoi, A.C., Sperduti, A.: A supervised self-organising map for structured data. In: Proc. WSOM 2001: Advances in Self-Organizing Maps, pp. 21–28. Springer, Heidelberg (2001)
Hammer, B., Micheli, A., Sperduti, A., Strickert, M.: A general framework for unsupervised processing of structured data. Neurocomputing (57), 3–35 (2004)
Haykin, S.: Neural networks: a comprehensive foundation, 2nd edn. Prentice-Hall, New Jersey (1999)
Sperduti, A.: Tutorial on neurocomputing of structures. In: Cloete, I., Zurada, J.M. (eds.) Knowledge-Based Neurocomputing, pp. 117–152. MIT Press, Cambridge (2000)
Sperduti, A.: Neural networks for adaptive processing of structured data. In: Dorffner, G., Bischof, H., Hornik, K. (eds.) ICANN 2001. LNCS, vol. 2130, pp. 5–12. Springer, Heidelberg (2001)
Scarselli, F., Gori, M., Tsoi, A.C., Hagenbuchner, M., Monfardini, G.: The Graph Neural Network Model. IEEE Transactions on Neural Networks 20(1), 61–80 (2009)
Andrejková, G., Oravec, J.: Rekurzívne neurónové siete a dátové štruktúry (Recursive neural networks and data stuctures). In: Proceedings of International Congress IMEM 2009, Catholic University, Ružomberok (2009)
Vančo, P., Farkáš, I.: Experimental comparison of recursive self-organizing maps for processing tree-structured data. Neurocomputing 73(7-9), 1362–1375 (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Andrejková, G., Oravec, J. (2011). Processing Acyclic Data Structures Using Modified Self-Organizing Maps. In: Cabestany, J., Rojas, I., Joya, G. (eds) Advances in Computational Intelligence. IWANN 2011. Lecture Notes in Computer Science, vol 6692. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21498-1_19
Download citation
DOI: https://doi.org/10.1007/978-3-642-21498-1_19
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-21497-4
Online ISBN: 978-3-642-21498-1
eBook Packages: Computer ScienceComputer Science (R0)