Recurrent neural networks are powerful learning machines capable of processing sequences. A recent extension of these machines can conveniently be used to process also general data structures like trees and graphs, which opens the doors to a number of new very interesting applications previously unexplored. In this paper, we show that when the problem of learning is restricted to purely symbolic data structures, like trees, the continuous representation developed after learning can also be given a symbolic interpretation. In particular, we show that a proper quantization of the neuron activation trajectory makes it possible to induce tree automata. We present preliminary experiments for small-size problems that, however, are very promising, especially when considering that this methodology is very robust with respect to accidental or malicious corruption of the learning set.

P., F., Gori, M., Maggini, M., Martinelli, E., G., S. (1997). Inductive Inference of Tree Automata by Recursive Neural Networks. In Proceedings of the 5th Congress of the Italian Association for Artificial Intelligence (pp.36-47). Springer Verlag [10.1007/3-540-63576-9_94].

Inductive Inference of Tree Automata by Recursive Neural Networks

GORI, MARCO;MAGGINI, MARCO;MARTINELLI, ENRICO;
1997-01-01

Abstract

Recurrent neural networks are powerful learning machines capable of processing sequences. A recent extension of these machines can conveniently be used to process also general data structures like trees and graphs, which opens the doors to a number of new very interesting applications previously unexplored. In this paper, we show that when the problem of learning is restricted to purely symbolic data structures, like trees, the continuous representation developed after learning can also be given a symbolic interpretation. In particular, we show that a proper quantization of the neuron activation trajectory makes it possible to induce tree automata. We present preliminary experiments for small-size problems that, however, are very promising, especially when considering that this methodology is very robust with respect to accidental or malicious corruption of the learning set.
1997
9783540635765
P., F., Gori, M., Maggini, M., Martinelli, E., G., S. (1997). Inductive Inference of Tree Automata by Recursive Neural Networks. In Proceedings of the 5th Congress of the Italian Association for Artificial Intelligence (pp.36-47). Springer Verlag [10.1007/3-540-63576-9_94].
File in questo prodotto:
File Dimensione Formato  
AIIA97.pdf

non disponibili

Tipologia: Post-print
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 758.81 kB
Formato Adobe PDF
758.81 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/11365/38430
 Attenzione

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