Distributed Knowledge Representation in Neural-Symbolic Learning Systems: A Case Study

May 2003

Proceedings of the Sixteenth International Florida Artificial Intelligence Research Society Conference (FLAIRS 2003)

Volume

Proceedings of the Sixteenth International Florida Artificial Intelligence Research Society Conference (FLAIRS 2003)

All Papers

Neural-symbolic integration concerns the integration of symbolic and connectionist systems. Distributed knowledge representation is traditionally seen under a purely symbolic perspective. In this paper, we show how neural networks can represent symbolic distributed knowledge, acting as multiagent systems with learning capability (a key feature of neural networks). We then apply our approach to the well-known muddy children puzzle, a problem used as a testbed for distributed knowledge representation formalisms. Finally, we sketch a full solution to this problem by extending our approach to deal with knowledge evolution over time.