Next CBR: Evolving CBR for multi-source experience and knowledge-rich applications
Supported by Spanish Ministry of Economy and Competitiveness under grant
- IIIA-CSIC: Instituto de Investigación en Inteligencia Artificial, Consejo Superior de Investigaciones Científicas
- GAIA-UCM: Grupo de Aplicaciones de Inteligencia Artificial, Universidad Complutense de Madrid
Case-based reasoning (CBR) combines in an effective manner both learning from experience and usage of domain knowledge. Techniques for case retrieval and reuse should not be studied in an isolated manner; instead they should be designed and evaluated in a framework that integrates different types of CBR systems as proposed in this project.
The goal of this project is to enlarge the capabilities of CBR systems to address three challenges we have identified as significant:
- The widespread use of ontologies today raises the issue that domain knowledge expressed in ontological frameworks has to be integrated not only in knowledge-intensive CBR but also in data-intensive CBR,
- The realization that all models are partial and each approximates reality raises the issue of CBR systems capable of using and integrating experience with multiple sources,
- The traditional emphasis on CBR research applied to the problem space raises the issue to focus more research on the solution space for improving the case reuse techniques, retrieval guidance techniques, and analyzing the solution space similarity structure.