Unified Integration of Explicit Knowledge and

Learning by Example in Recurrent Networks ?

Paolo Frasconi, Student Member, IEEE

Marco Gori, Member, IEEE Marco Maggini

Giovanni Soda, Member, IEEE

1

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 of uncertain information management. We present preliminary results for problems of automatic speech recognition.
Index Terms - Recurrent neural networks, learning automata, automatic speech recognition.

I Introduction

The resurgence of interest in connectionist models has led several researchers to investigate their application to the building of intelligent systems". Unlike symbolic models proposed in artificial intelligence, learning plays a central role in connectionist models. Many successful applications have mainly concerned perceptual tasks (see e.g. [2, 6, 10, 20]),

?This research was partially supported by MURST 40% and CNR Grant 90.01530.CT01. 1The authors are with Dipartimento di Sistemi e Informatica, Universit?a di Firenze, Via di Santa Marta 3 - 50139 Firenze - Italy, Tel. (39) 55-4796265 - Telex 580681 UNFING I - Fax (39) 55-4796363, e-mail : [email protected]