Recursive neural networks are a powerful tool for processing structured data. According to the recursive learning paradigm, the information to be processed 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 disordered and cyclic. In this paper, a methodology is proposed which allows us to map any cyclic directed graph into a “recursive–equivalent” tree. Therefore, the computational power of recursive networks is definitely established, also clarifying the underlying limitations of the model. The subgraph–isomorphism detection problem was used for testing the approach, showing very promising results.

Bianchini, M., Gori, M., Sarti, L., Scarselli, F. (2003). BackPropagation Through Cyclic Structures. In Proceedings del VIII Congresso Nazionale Associazione Italiana Intelligenza Artificiale (pp.118-129) [10.1007/978-3-540-39853-0_10].

BackPropagation Through Cyclic Structures

BIANCHINI, MONICA;GORI, MARCO;SARTI, LORENZO;SCARSELLI, FRANCO
2003-01-01

Abstract

Recursive neural networks are a powerful tool for processing structured data. According to the recursive learning paradigm, the information to be processed 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 disordered and cyclic. In this paper, a methodology is proposed which allows us to map any cyclic directed graph into a “recursive–equivalent” tree. Therefore, the computational power of recursive networks is definitely established, also clarifying the underlying limitations of the model. The subgraph–isomorphism detection problem was used for testing the approach, showing very promising results.
354020119X
Bianchini, M., Gori, M., Sarti, L., Scarselli, F. (2003). BackPropagation Through Cyclic Structures. In Proceedings del VIII Congresso Nazionale Associazione Italiana Intelligenza Artificiale (pp.118-129) [10.1007/978-3-540-39853-0_10].
File in questo prodotto:
File Dimensione Formato  
AIIA03.pdf

non disponibili

Tipologia: Post-print
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 209.12 kB
Formato Adobe PDF
209.12 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/11365/28689
 Attenzione

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