Abstract
Case-Based Reasoning (CBR) applies past experience to solve new problems with suitable solutions. This approach presents overloading queries to adapt solutions if necessary. Subpar solutions have to be adapted within a CBR cycle before retaining them to keep a good quality of the case base. Dealing with missing values can be seen as previous step to avoid unnecessary adaptations. Integrate efficient and useful adaptations can be seen as really interesting and challenging task when considering the full CBR methodology. The common CBR principle -similar problems are having similar solutions- can be seen as a rather good point of start when developing an adaptation feature. An adaptation concept and first experience are presented within this paper.
Original language | English |
---|---|
Title of host publication | INFORMATION, PROCESS, AND KNOWLEDGE MANAGEMENT. INTERNATIONAL CONFERENCE. 5TH 2013. (EKNOW 2013) |
Editors | Dirk Malzahn |
Publisher | Curran Associates, Inc. |
Number of pages | 4 |
ISBN (Print) | 978-1-61208-254-7 |
Publication status | Published - Feb 2013 |
Fields of science
- 102 Computer Sciences
- 102001 Artificial intelligence
JKU Focus areas
- Computation in Informatics and Mathematics