Recursive neural networks are a new connectionist model particularly tailored to process Directed Positional Acyclic Graphs (DPAGs). 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 are given, able to guarantee that the approximation capabilities are maintaned, despite of the weight sharing.

Bianchini, M., Gori, M., Scarselli, F. (2001). Recursive processing of directed acyclic graphs. In Neural Nets - Proceedings of WIRN 2001 (pp.96-101). New York : Springer.

Recursive processing of directed acyclic graphs

BIANCHINI, MONICA;GORI, MARCO;SCARSELLI, FRANCO
2001-01-01

Abstract

Recursive neural networks are a new connectionist model particularly tailored to process Directed Positional Acyclic Graphs (DPAGs). 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 are given, able to guarantee that the approximation capabilities are maintaned, despite of the weight sharing.
2001
9781852335052
Bianchini, M., Gori, M., Scarselli, F. (2001). Recursive processing of directed acyclic graphs. In Neural Nets - Proceedings of WIRN 2001 (pp.96-101). New York : Springer.
File in questo prodotto:
File Dimensione Formato  
WIRN01.pdf

non disponibili

Tipologia: Post-print
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 190.93 kB
Formato Adobe PDF
190.93 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11365/24104
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo