Recursive neural networks are a powerful tool for processing structured data, thus filling the gap between connectionism, which is usually related to poorly organized data, and a great variety of real-world problems, where the information is naturally encoded in the relationships among the basic entities. In this paper, some theoretical results about linear recursive neural networks are presented that allow us to establish conditions on their dynamical properties and their capability to encode and classify structured information. A lot of the limitations of the linear model, intrinsically related to recursive processing, are inherited by the general model, thus establishing also their computational capabilities and range of applicability. As a byproduct of our study some connections with the classical linear system theory are given where the processing is extended from sequences to graphs.

Bianchini, M., Gori, M., Scarselli, F. (2001). Theoretical properties of recursive neural networks with linear neurons. IEEE TRANSACTIONS ON NEURAL NETWORKS, 12(5), 953-967 [10.1109/72.950127].

Theoretical properties of recursive neural networks with linear neurons

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

Abstract

Recursive neural networks are a powerful tool for processing structured data, thus filling the gap between connectionism, which is usually related to poorly organized data, and a great variety of real-world problems, where the information is naturally encoded in the relationships among the basic entities. In this paper, some theoretical results about linear recursive neural networks are presented that allow us to establish conditions on their dynamical properties and their capability to encode and classify structured information. A lot of the limitations of the linear model, intrinsically related to recursive processing, are inherited by the general model, thus establishing also their computational capabilities and range of applicability. As a byproduct of our study some connections with the classical linear system theory are given where the processing is extended from sequences to graphs.
2001
Bianchini, M., Gori, M., Scarselli, F. (2001). Theoretical properties of recursive neural networks with linear neurons. IEEE TRANSACTIONS ON NEURAL NETWORKS, 12(5), 953-967 [10.1109/72.950127].
File in questo prodotto:
File Dimensione Formato  
RECLIN-TNN.pdf

non disponibili

Tipologia: Post-print
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 338.07 kB
Formato Adobe PDF
338.07 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/11365/22108
 Attenzione

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