Abstract
The aim of this study is to introduce a fuzzy model to process structured data. A structured organization of information is typically required by symbolic processing. Most connectionist models assume that data are organized in a form of relatively simple structures such as vectors or sequences. In this work, we propose a connectionist model that can directly process labeled trees. The model is based on a new category of logic connectives and logic neurons that use the concept of uninorms. Uninorms are a generalization of t-norms and t-conorms used for aggregating fuzzy sets. Using a back-propagation algorithm we optimize the parameters of the model (relations and membership functions). The learning issues are presented and some experimental results obtained for synthetic realistic data, are reported.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Calvo, T., Mesiar, R.: Continuous Generate Associative Aggregation Operators. Fuzzy Sets and Systems 126, 191–197 (2002)
Bianchini, M., Maggini, M., Martinelli, E., Sarti, L., Scarselli, F.: Recursive Neural Networks for Processing Graphs with Labelled Edges: Theory and Applications. Neural Networks 18, 1040–1050 (2005)
Ciaramella, A., Pedrycz, W., Tagliaferri, R.: The Genetic Development of Ordinal Sums. Fuzzy Sets and Systems 151, 303–325 (2005)
Ciaramella, A., Pedrycz, W., Tagliaferri, R.: OR/AND Neurons for Fuzzy Set Connectives Using Ordinal Sums and Genetic Algorithms. In: Bloch, I., Petrosino, A., Tettamanzi, A.G.B. (eds.) WILF 2005. LNCS (LNAI), vol. 3849, pp. 188–194. Springer, Heidelberg (2006)
Ciaramella, A., Pedrycz, W., Tagliaferri, R.: The Genetic Development of Uninorms Based Neurons. In: Masulli, F., Mitra, S., Pasi, G. (eds.) WILF 2007. LNCS, vol. 4578, pp. 69–76. Springer, Heidelberg (2007)
Fodor, J.C., Yager, R.R., Rybalov, A.: Structure of Uninorms. Int. J. of Uncertainty, Fuzziness and Knowledge-Based Systems 5, 411–427 (1997)
Frasconi, P., Gori, M., Sperduti, A.: A General Framework for Adaptive Processing of Data Structures. IEEE Transaction on Neural Networks 9(5), 768–786 (1998)
Gori, M., Petrosino, A.: Encoding Nondeterministic Fuzzy Tree Automata Into Recursive Neural Networks. IEEE Transactions on Neural Networks 15(6), 1435–1449 (2004)
Hirota, K., Pedrycz, W.: OR/AND Neuron in Modeling Fuzzy Set Connectives. IEEE Transaction on Fuzzy Systems 2, 151–161 (1994)
Kuchler, A., Goller, C.: Inductive Learning in Symbolic Domains Using Structure-Driven Recurrent Neural Networks. In: Görz, G., Hölldobler, S. (eds.) KI 1996. LNCS, vol. 1137, pp. 183–197. Springer, Heidelberg (1996)
Klement, E.P., Mesiar, R., Pap, E.: Triangular Norms. Kluwer Academic Publishers, Dordrecht (2001)
Pedrycz, W.: Logic-Based Fuzzy Neurocomputing with Unineurons. IEEE Transaction on Fuzzy Systems 14(6), 860–873 (2006)
Sperduti, A., Starita, A.: Supervised Neural Networks for the Classification of Structures. IEEE Transaction on Neural Networks 8(3) (1997)
Yager, R.R.: Uninorms in Fuzzy Systems Modeling. Fuzzy Sets and Systems 122, 167–175 (2001)
Zuckerman, M.-M.: Ordinal Sum-Sets. Proceedings of Americal Mathematical Society 35(1), 242–248
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ciaramella, A., Pedrycz, W., Petrosino, A. (2009). Uninorm Based Fuzzy Network for Tree Data Structures. In: Di Gesù, V., Pal, S.K., Petrosino, A. (eds) Fuzzy Logic and Applications. WILF 2009. Lecture Notes in Computer Science(), vol 5571. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-02282-1_10
Download citation
DOI: https://doi.org/10.1007/978-3-642-02282-1_10
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-02281-4
Online ISBN: 978-3-642-02282-1
eBook Packages: Computer ScienceComputer Science (R0)