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 multi-agent 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.
展开▼
