Knowledge discovery is a key element and challenge in the Case Based Reasoning problem solving process. By its nature, knowledge discovery is usually uncertain and in order to make effective use of discovered knowledge, the types of uncertainty need to be determined and dealt with using appropriate methods and techniques. Discoveries can be naturally imprecise, stochastic, and fuzzy and subject to prescribed tolerances. Uncertainty can also affect the useful application of knowledge discoveries in the CBR cycle and can raise issues of confidence, possibly making the ensuing reasoning unconvincing to its end users.
As a key component capturing discovered knowledge in Case Based-Reasoning, similarity needs to deal with uncertainty. This is a particular challenge in knowledge areas with complex, approximate, imprecise cases and heterogeneous domains: The domain knowledge underlying the specification of similarity measures or the adaptation of retrieved solutions is usually uncertain and incomplete. Moreover, as problem solving in CBR is primarily of heuristic nature, various aspects of uncertainty also emerge within the case-based processing of knowledge. Indeed, these sources of uncertainty are inherent to CBR and actually concern all phases of the case-based problem-solving process and are relevant in all CBR knowledge containers.
Case-based reasoning must face the challenge to deal with uncertain, incomplete, and vague information, which leads to the need of suitable methods for modeling and reasoning under uncertainty, appropriately complemented by tools for learning and knowledge discovery. Over the past years there has been increased interest in formalizing parts of the CBR methodology within different frameworks of reasoning under uncertainty, and in building hybrid approaches by combining CBR with methods of uncertain and approximate reasoning and soft computing.
The objective of the workshop is to provide an opportunity for exchanging ideas related to the application of various techniques of uncertainty management, knowledge discovery, and similarity in CBR. The workshop aims at providing a forum for the discussion of recent advances in this research field and to offer an opportunity for researchers and practitioners to identify new promising research directions.
The organizers welcome contributions on the use of principled methods for reasoning under uncertainty, knowledge discovery, and similarity, such as:
in case-based reasoning, including but not limited to:
