Abstract
Recursive neural networks axe a new connectionist model particularly tailored to process Directed Positional Acyclic Graphs (DPAGs) [4]. While this assumption is reasonable in some applications, it introduces unnecessary constraints in others. In this paper, it is shown that the constraint on the ordering can be relaxed by using an appropriate weight sharing, that guarantees the independence of the network output with respect to the permutations of the arcs leaving from each node. Some theoretical properties of the proposed architecture axe given, able to guarantee the approximation capabilities are maintained, despite of the weight sharing.
This is a preview of subscription content, log in via an institution to check access.
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
M. Bianchini, M. Gori, and F. Scarselli. Recursive networks: An overview of theoretical results. In M. Marinaro and R. Tagliaferri, editors, Neural Nets — WIRN ‘99, pages 237–242. Springer, Vietri (Salerno, Italy), 1999.
M. Bianchini, M. Gori, and F. Scarselli. Theoretical properties of recursive networks with linear neurons. Technical Report DII-31/99, Dip. di Ingegneria dell’Informazione, Università di Siena, Siena, Italy, 1999. submitted to IEEE Trans. on Neural Networks.
M. Bianchini, M. Gori, and F. Scarselli. Processing directed acyclic graphs with recursive neural networks. Submitted to “IEEE Transactions on Neural Networks”, 2000.
P. Frasconi, M. Gori, and A. Sperduti. A general framework for adaptive processing of data structures. IEEE Transactions on Neural Networks, 9(5):768–786, September 1998.
B. Hammer. Approximation capabilities of folding networks. In ESANN ‘99, pages 33–38, Bruges, (Belgium), April 1999.
Y. leCun, L. Bottou, Y. Bengio, and P. Haffner. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278–2324, 1998.
Author information
Authors and Affiliations
Consortia
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag London Limited
About this paper
Cite this paper
Bianchini, M., Gori, M., IEEE Fellow., Scarselli, F. (2002). Recursive Processing of Directed Acyclic Graphs. In: Tagliaferri, R., Marinaro, M. (eds) Neural Nets WIRN Vietri-01. Perspectives in Neural Computing. Springer, London. https://doi.org/10.1007/978-1-4471-0219-9_6
Download citation
DOI: https://doi.org/10.1007/978-1-4471-0219-9_6
Publisher Name: Springer, London
Print ISBN: 978-1-85233-505-2
Online ISBN: 978-1-4471-0219-9
eBook Packages: Springer Book Archive