Extraction of Design Patterns from Evolutionary Algorithms Using Case-Based Reasoning
ICES '01 Proceedings of the 4th International Conference on Evolvable Systems: From Biology to Hardware
Case-Based Initialization of Genetic Algorithms
Proceedings of the 5th International Conference on Genetic Algorithms
An Evolutionary Agent Model of Case-Based Classification
EWCBR '96 Proceedings of the Third European Workshop on Advances in Case-Based Reasoning
Modelling the Competence of Case-Bases
EWCBR '98 Proceedings of the 4th European Workshop on Advances in Case-Based Reasoning
Towards Improving Case Adaptability with a Genetic Algorithm
ICCBR '97 Proceedings of the Second International Conference on Case-Based Reasoning Research and Development
Evolutionary Case Based Design
Proceedings of the First United Kingdom Workshop on Progress in Case-Based Reasoning
Robustness of Case-Initialized Genetic Algorithms
Proceedings of the Twelfth International Florida Artificial Intelligence Research Society Conference
Categorizing Case-Base Maintenance: Dimensions and Directions
EWCBR '98 Proceedings of the 4th European Workshop on Advances in Case-Based Reasoning
Combining CBR and GA for Designing FPGAs
ICCIMA '99 Proceedings of the 3rd International Conference on Computational Intelligence and Multimedia Applications
Genetic algorithms for feature relevance assignment in memory-based language processing
ConLL '00 Proceedings of the 2nd workshop on Learning language in logic and the 4th conference on Computational natural language learning - Volume 7
Remembering to add: competence-preserving case-addition policies for case-base maintenance
IJCAI'99 Proceedings of the 16th international joint conference on Artifical intelligence - Volume 1
A hybrid genetic algorithm for classification
IJCAI'91 Proceedings of the 12th international joint conference on Artificial intelligence - Volume 2
| Hi-index | 0.00 |
In certain domains a case base may contain contradictory but correct cases.The contradictory solutions are due to known domain and problem characteristics which are not part of the case description, and which cannot be formally or explicitly described.In such situations it is important to develop methods that will use these criteria to select among the competing solutions of the matching cases Our domain of application was the assignment of billing numbers to the shipment of goods, and the case base contained numerous cases of similar or even identical problems that had different solutions (billing numbers).Suc h contradictory solutions were correct and an outcome of domain constraints and characteristics that were not part of the cases and were also not formally known and defined.It was assumed that the frequency with which a solution appeared among the retrieved cases and the recency of the time the solution had been applied were important for selecting among competing solutions, but there was no explicit way for doing so.In this paper we show how we used genetic algorithms to discover methods to combine and operationalize vague selection criteria such as "recency" and "frequency." GAs helped us discover selection criteria for the contradictory solutions retrieved by CBR retrieval and significantly improved the accuracy and performance of the CBR system.