In the last few years it has been shown that recurrent neural networks are adequate for processing general data structures like trees and graphs, which opens the doors to a number of new interesting applications previously unexplored. In this paper, we analyze the efficiency of learning the membership of DO AGs (Directed Ordered Acyclic Graphs) in terms of local minima of the error surface by relying on the principle that their absence is a guarantee of efficient learning. We give sufficient conditions under which the error surface is local minima free. Specifically, we define a topological index associated with a collection of DOAGs that makes it possible to design the architecture so as to avoid local minima.

Frasconi, P., Gori, M., & Sperduti, A. (1997). On the Efficient Classification of Data Structures Neural Networks. In Proceedings of IJCAI1997 (pp.1066-1071). San Francisco : MORGAN KAUFMANN PUB INC.

On the Efficient Classification of Data Structures Neural Networks

GORI, MARCO;
1997

Abstract

In the last few years it has been shown that recurrent neural networks are adequate for processing general data structures like trees and graphs, which opens the doors to a number of new interesting applications previously unexplored. In this paper, we analyze the efficiency of learning the membership of DO AGs (Directed Ordered Acyclic Graphs) in terms of local minima of the error surface by relying on the principle that their absence is a guarantee of efficient learning. We give sufficient conditions under which the error surface is local minima free. Specifically, we define a topological index associated with a collection of DOAGs that makes it possible to design the architecture so as to avoid local minima.
1-55860-480-4
Frasconi, P., Gori, M., & Sperduti, A. (1997). On the Efficient Classification of Data Structures Neural Networks. In Proceedings of IJCAI1997 (pp.1066-1071). San Francisco : MORGAN KAUFMANN PUB INC.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

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: http://hdl.handle.net/11365/38647
 Attenzione

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