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

See also:

• Other MIX servers

Keywords:

Symbolic-Connectionist Integration, Machine Learning, Hybrid Learning, Knowledge-Based Systems, Distributed Artificial Intelligence

Project Objectives:

The goal of this project is to advance the state of the art in symbolic-connectionist integration (SCI); more specifically, it aims to:

• enhance the versatility of symbolic-connectionist hybrid systems (SCSs) by combining a variety of representation, inferencing and learning schemes from the symbolic and the connectionist paradigms
• augment the reasoning power of SCSs by overcoming their traditional limitation to propositional logic
• clarify the theoretical impact of symbolic-connectionist integration on fundamental machine learning issues such as the choice and combination of learning methods, credit assignment and knowledge assimilation
• ensure the scalability and real-world applicability of the resulting hybrid models by testing them on prediction, optimization and classification problems in industrial and other areas.

Approaches 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 specialize 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 or model-based reasoning to form partial hybrids, which will then be integrated within a single unified model.

Potential Impact:

The immediate theoretical result of this project will be a gain of insight into the complex problems entailed by SCI. A wider-ranging consequence will be in the field of machine learning, where multistrategy learning remains essentially symbolic. This is the first medium-scale effort we know of to implement multiparadigm, multistrategy learning in knowledge-based systems. From the practical point of view, hybrid models might 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 in the software engineering industry.

Complementary Information:

MIX is an ESPRIT III Basic Research Project financed jointly by the European Union and the Swiss Federal Government from 1994 to 1996. Project partners are:

• INRIA-Lorraine, Coordinator (France)
• CUI - Université de Genève (Switzerland)
• Institut de Mathématiques Appliquées de Grenoble (France)
• Kratzer Automatisierung (Germany)
• Technische Universität München (Germany)
• Universidad Politécnica de Madrid (Spain)