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, a methodology is proposed, which allows us to process any cyclic directed graph. Therefore, the computational power of recursive networks is definitely established, also clarifying the underlying limitations of the model.
Bianchini, M., Gori, M., Sarti, L., Scarselli, F. (2006). Recursive Processing of Cyclic Graphs. IEEE TRANSACTIONS ON NEURAL NETWORKS, 17(1), 10-18 [10.1109/TNN.2005.860873].
Recursive Processing of Cyclic Graphs
BIANCHINI, MONICA;GORI, MARCO;SARTI, LORENZO;SCARSELLI, FRANCO
2006-01-01
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, a methodology is proposed, which allows us to process any cyclic directed graph. Therefore, the computational power of recursive networks is definitely established, also clarifying the underlying limitations of the model.File | Dimensione | Formato | |
---|---|---|---|
TNN-06.PDF
non disponibili
Tipologia:
Post-print
Licenza:
NON PUBBLICO - Accesso privato/ristretto
Dimensione
567.5 kB
Formato
Adobe PDF
|
567.5 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.
https://hdl.handle.net/11365/22014
Attenzione
Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo