Integration of Different Information Processing Methods
A way of integrating different information-processing methods is discussed. By analyzing various methods a possible way of integrating dynamically these methods is studied. A special processor to combine different methods is necessary for integration. It is called an integrator. Among various information-processing methods, only declarative knowledge-based method is suited for an integrator. Then the realistic way of developing the integrator is discussed. Even with this integrator however the scope of actual integration is limited because of a big gap existing between symbolic and non-symbolic methods of information processing. The difference between symbolic and non-symbolic methods is clarified by representing them by the same mathematical formula and based on this result a possible extension of knowledge-based processing is proposed in order to expand the scope of integration.
KeywordsNeural Network Logical Structure Knowledge Processing Logical Expression Symbolic Form
Unable to display preview. Download preview PDF.
- V. Honavar and L. Uhr (eds.); Artificial Intelligence and Neural Networks, Steps toward Principled Integration, Academic press, 1994.Google Scholar
- L. Monostori, Cs. Egresits, and B. Kadar; Hybrid AI Solution and their Application in Manufacturing, Proc.Ninth International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems, Gordon and Breach Publishers, 1996.Google Scholar
- S. Ohsuga; Toward Truly Intelligent Information Systems - From Expert Systems to Automatic Programming, Knowledge-Based Systems, Vol. l0, 363-396, 1998.Google Scholar
- F. Hays-Ross; Artificial Intelligence, What Works and What Doesn’t ? Magazine, Volume 18, No. 2, 1997Google Scholar
- S. Ohsuga; Symbol processing by Non-Symbol Processor, Proc. 4th Pacific Rim International Conference on Artificial Intelligence, 1996, Cairns, Australia.Google Scholar