WIRN 2005, NAIS 2005: Neural Nets pp 38-43 | Cite as
Recursive Neural Networks and Graphs: Dealing with Cycles
Abstract
Recursive neural networks are a powerful tool for processing structured data. According to the recursive learning paradigm, the input information consists of directed positional acyclic graphs (DPAGs). In fact, recursive networks are fed following the partial order defined by the links of the graph. Unfortunately, the hypothesis of processing DPAGs is sometimes too restrictive, being the nature of some real–world problems intrinsically cyclic. In this paper, the methodology proposed in [1,2] to process cyclic directed graphs is tested on some interesting problems in the field of structural pattern recognition. Such preliminary experimentation shows very promising results.
Preview
Unable to display preview. Download preview PDF.
References
- 1.Bianchini, M., Gori, M., Sarti, L., Scarselli, F.: Recursive processing of cyclic graphs. IEEE Transactions on Neural Networks with 17(1), 10–18 (2006)CrossRefGoogle Scholar
- 2.Bianchini, M., Gori, M., Scarselli, F.: Recursive processing of cyclic graphs. In: IEEE International Joint Conference on Neural Networks, pp. 154–159 (2002)Google Scholar
- 3.Frasconi, P., Gori, M., Sperduti, A.: A general framework for adaptive processing of data structures. IEEE Transactions on Neural Networks 9, 768–786 (1998)CrossRefGoogle Scholar
- 4.Sperduti, A., Starita, A.: Supervised neural networks for the classification of structures. IEEE Transactions on Neural Networks 8, 429–459 (1997)CrossRefGoogle Scholar
- 5.Gori, M., Maggini, M., Martinelli, E., Scarselli, F.: Learning user profiles in NAUTILUS. In: International Conference on Adaptive Hypermedia and Adaptive Web–based Systems, Trento (Italy) (2000)Google Scholar
- 6.Bianchini, M., Maggini, M., Sarti, L., Scarselli, F.: Recursive neural networks learn to localize faces. Pattern Recognition Letters 26, 1885–1895 (2005)CrossRefGoogle Scholar
- 7.Küchler, A., Goller, C.: Inductive learning in symbolic domains using structure– driven recurrent neural networks. In: Görz, G., Hölldobler, S. (eds.) Advances in Artificial Intelligence, pp. 183–197. Springer, Heidelberg (1996)Google Scholar
- 8.Bianchini, M., Mazzoni, P., Sarti, L., Scarselli, F.: Face spotting in color images using recursive neural networks. In: Gori, M., Marinai, S. (eds.) IAPR–TC3 International Workshop on Artificial Neural Networks in Pattern Recognition, Florence (Italy), pp. 76–81 (2003)Google Scholar
- 9.Bianchini, M., Gori, M., Mazzoni, P., Sarti, L., Scarselli, F.: Face localization with recursive neural networks. In: Apolloni, B., Marinaro, M., Tagliaferri, R. (eds.) WIRN 2003, vol. 2859, pp. 99–105. Springer, Heidelberg (2003)CrossRefGoogle Scholar
- 10.Bianchini, M., Maggini, M., Sarti, L., Scarselli, F.: Recursive neural networks for object localization. In: Proceedings of IJCNN 2004, Budapest (Hungary), vol. 3, pp. 1911–1915. IEEE, Los Alamitos (2004)Google Scholar