Modular Integration of Connectionist and Symbolic Processing in Knowledge-Based Systems


MIX - 9119

Work Area: Basic Aspects of Multiple Computing Agents

Keywords symbolic-connectionist integration, machine learning, hybrid learning, knowledge-based systems, distributed artificial intelligence


Start Date: to be announced / Status: starting

[ participants / contact ]


Abstract MIX will investigate strategies and develop tools for the integration of symbolic and connectionist processing in knowledge-based systems. A variety of hybrid models will be implemented through the cooperation of intelligent agents in a distributed architecture. Foreseen applications would address problems in the automobile and steel industries and in the medical domain.


Aims

The goal of this project is to advance the state of the art in symbolic-connectionist integration (SCI), and the work will aim to:

Approach and Methods

Current SCSs are small experimental systems which ally one symbolic and one connectionist model using simple, often ad hoc coupling modes and techniques. To blend a wider range of models from the two paradigms within a coherent system, a principled approach is required which takes account of final integration needs in the design of the individual components. We have chosen a distributed approach to SCI. An initial phase of the project will consist in the specification and implementation of a distributed architecture for the cooperation of multiple heterogeneous agents. At the outset generic agents will draw from any of the processing models within the two paradigms to accomplish their given tasks. With problem-solving experience, however, each will specialise more and more on methods best adapted to its specific problem context. These methods will be based on a broad repertoire of inferencing and learning strategies which will be made available by the hybrid models built in the project. These hybrid models will be created in a modular and incremental fashion. Neural networks will be combined with fuzzy logic, case-based reasoning to form partial hybrids, which will then be integrated within a single unified model.

Potential

A result of this project will be insight into the complex problems of SCI. In the field of machine learning, where multistrategy learning remains essentially symbolic, this will be the first medium-scale effort we know of to implement multiparadigm, multistrategy learning in knowledge-based systems. From a practical point of view, hybrid models should give a new impetus to the incorporation of AI techniques in industrial applications where purely symbolic or purely connectionist processing models have been found wanting. Advances in SCI are also expected to have an impact on the software engineering industry.

Further information about MIX is available from the MIX home page <URL:http://www.loria.fr/exterieur/equipe/rfia/cortex/mix/mix.html>.


Coordinator

INRIA-Lorraine - F
P.O. Box 239
Campus Universitaire
F- 54506 Vandoeuvre-les-Nancy Cedex

Partners

Kratzer Automatisierung - D
Technische Universität München - D
Universidad Politécnica de Madrid - E
Institut de Mathématiques Appliquées de Grenoble - F
Centre Unversitaire d'Informatique - Université de Genève - CH

CONTACT POINT

Prof. Jean-Paul Haton
tel +33/83 59 20 50
fax +33/83 41 30 79
e-mail: jph@loria.fr


LTR synopses home page LTR work area index LTR acronym index LTR number index LTR Projects index
All synopses home page all acronyms index all numbers index

MIX - 9119, August 1994


please address enquiries to the ESPRIT Information Desk

html version of synopsis by Nick Cook