We propose a novel unified approach for integrating explicit knowledge and learning by example in recurrent networks. The explicit knowledge is represented by automaton rules, which are directly injected into the connections of a network. This can be accomplished by using a technique based on linear programming, instead of learning from random initial weights. Learning is conceived as a refinement process and is mainly responsible for uncertain information management. We present preliminary results for problems of automatic speech recognition.

P., F., Gori, M., Maggini, M., & G., S. (1995). Unified integration of explicit knowledge and learning by example in recurrent networks. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 7(2), 340-346 [10.1109/69.382304].

Unified integration of explicit knowledge and learning by example in recurrent networks

GORI, MARCO;MAGGINI, MARCO;
1995

Abstract

We propose a novel unified approach for integrating explicit knowledge and learning by example in recurrent networks. The explicit knowledge is represented by automaton rules, which are directly injected into the connections of a network. This can be accomplished by using a technique based on linear programming, instead of learning from random initial weights. Learning is conceived as a refinement process and is mainly responsible for uncertain information management. We present preliminary results for problems of automatic speech recognition.
File in questo prodotto:
File Dimensione Formato  
TKDE95.pdf

non disponibili

Tipologia: Post-print
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 531.83 kB
Formato Adobe PDF
531.83 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: http://hdl.handle.net/11365/31137
 Attenzione

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