Abstract
Modelling of neural networks is still a very interesting and important field in the area of computing models. If input domains of neural networks are data structures represented by graphs and output domain is expected in a similar form, it is necessary to consider it in the process of neural network modelling. We propose four models of extended Self Organizing Maps (SOM) that can be applied to graph data structures as input and output domains together with learning algorithms. Extensions of the SOM model are based on the idea to remember information of connections in data structures (using some context neurons).
With regards to the evaluation of developed models and trained structures, we used data from the study programs of the Faculty of Science, P.J. Šafárik University in Košice. We evaluated the ability of models to enumerate output descendants of a node in a graph structure and the ability to interpret structures by developed neural networks. We also evaluated the quality of the developed networks in a learning process.
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
Aiolli, F., Da San Martino, G., Hagenbuchner, M., Sperdutti, A.: Self-organizing Maps for Structured Domains: Theory, Models, and Learning of Kernels. In: Bianchini, M., Maggini, M., Scarselli, F., Jain, L.C. (eds.) Innovations in Neural Infor. Paradigms & Appli. 247, vol. SCI, pp. 9–42. Springer, Heidelberg (2009), www.springerlink.com
Andrejková, G., Oravec, J.: Application of modified SOM Neural Networks on Acyclic Data Structures. Acta Electrotechnica et Informatica 12(2), 3–8 (2012)
Andrejková, G., Oravec, J.: Combination SOM neural network model and a layer for a traning with supervisor. In: Tatras, H. (ed.) Proc. of Cognition and Artificial Life, pp. 1–10 (2013) (in Slovak)
Chappell, G.J., Taylor, J.G.: The temporal Kohonen map. Neural Networks 6, 441–445 (1993)
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, July 25-29, vol. 3, pp. 1923–1928 (2004)
Hagenbuchner, M., Tsoi, C.A., Sperduti, A.: A supervised self-organising map for structured data. In: Proc. WSOM 2001: Advances in Self-Organizing Maps, pp. 21–28. Springer (2001)
Hammer, B., Micheli, A., Sperduti, A., Strickert, M.: A general framework for unsupervised processing of structured data. Neurocomputing 57, 3–35 (2004)
Hammer, B., Micheli, A., Sperduti, A., Strickert, M.: Recursive self-organizing network models. Neural Networks 17(8-9), 1061–1085 (2004)
Haykin, S.: Neural networks: a comprehensive foundation, 2nd edn. Prentice-Hall, New Jersey (1999)
Kohonen, T.: Self-organized formation of topologically correct feature map. Biological Cybernetics, 43, 56–69
Kohonen, T.: Essentials of the self-organizing map. Neural Networks 37, 52–65 (2013)
Koskela, T., Varsta, M., Heikkonen, J., Kaski, K.: Temporal sequence processing using recurrent SOM. In: Proceedings of the 2nd International Conference on Knowledge-Based Intelligent Engineering Systems, pp. 290–297 (1998)
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, H., Monfardini, G.: The Graph Neural Network Model. IEEE Transactions on Neural Networks 20(1), 61–80 (2009)
Strickert, M., Hammer, B.: Self-organizing context learning. In: European Symposium on Artificial Neural Networks (ESANN), pp. 39–44. D-side Publications (2004)
Vančo, P., Farkáš, I.: Experimental comparison of recursive self-organizing maps for processing tree-structured data. Neurocomputing 73(7-9), 1362–1375 (2010)
Voegtlin, T.: Recursive self-organizing maps. Neural Networks 15(8-9), 979–991 (2002)
Yin, H.: The Self-organizing Maps: Background, Theories, Extensions and Applications. In: Fulcher, J., Jain, L.C. (eds.) Computational Intelligence: A Compendium. SCI, vol. 115, pp. 715–762. Springer, Heidelberg (2008)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Andrejková, G., Oravec, J. (2015). Extended Self Organizing Maps for Structured Domain: Models and Learning. In: Sinčák, P., Hartono, P., Virčíková, M., Vaščák, J., Jakša, R. (eds) Emergent Trends in Robotics and Intelligent Systems. Advances in Intelligent Systems and Computing, vol 316. Springer, Cham. https://doi.org/10.1007/978-3-319-10783-7_24
Download citation
DOI: https://doi.org/10.1007/978-3-319-10783-7_24
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-10782-0
Online ISBN: 978-3-319-10783-7
eBook Packages: EngineeringEngineering (R0)