| M. Lenz. Case Retrieval Nets applied to large case bases. Proc. 4th German Workshop on CBR, Berlin, 1996. Humboldt University. |
....Ramsey and Grefenstette (1994) defined a case as a (genetically induced) rule population. Their CBL algorithm uses environmental cues to select which population to use in response to concept drifts. Finally, case retrieval nets represent cases as sets of entities in a joint semantic network. Lenz (1996) described their application to classification tasks. 2.2 Learning retrieval knowledge Complex representations and tasks (e.g. planning) require learning algorithms tailored to their case retrieval and revision needs. For example, CAPlan CbC (Mu noz Avila Hullen, 1996) learns feature weights ....
Lenz, M. (1996). Case retrieval nets applied to large case bases. Fourth German Workshop on Case-Based Reasoning: System Development and Evaluation (pp.
....cf. 9] CRNs are more generally applicable and do rest on a sound formal framework which allows for the investigation of properties. Besides the theoretical investigations, we already performed a number of empirical tests with CRNs. The complete documentation of the results can be found in [7]. Before we go into the details about CRNs, we would like to outline what we consider as requirements for a case retrieval technique. Basically, there are three conditions to be met: efficiency, completeness, and flexibility (cf. also [3, 17] Efficiency concerns the effort required to access ....
....ff 2 (c) of case nodes c 2 C. Case based systems with attribute vectors often use a similarity measure which is computed as the weighted sum of attribute similarities (composite similarities) These can easily be implemented by special BCRNs ( 10] As experiments show (cf. Section 5 and [7]) the implementation of case retrieval using CRNs is efficient. Moreover, B)CRNs offer the possibilities of extensions in various ways, some of which will be given now. 4 Extensions of Case Retrieval Nets While Section 3 presented a formal model of the most basic type of Case Retrieval Nets, ....
[Article contains additional citation context not shown here]
M. Lenz. Case Retrieval Nets applied to large case bases. Proc. 4th German Workshop on CBR, Berlin, 1996. Humboldt University.
....Nets (CRNs) This can be seen as an extension to ABS in that CRNs are more generally applicable and that they rest on a sound formal framework which allows the investigation of properties. We already performed a number of empirical tests with CRNs. The documentation of the results can be found in [5]. Before we go into the details about CRNs, we would like to outline what we consider as requirements for a case retrieval technique. Basically, there are three major conditions to be met: efficiency, completeness, and flexibility (cf. also [12, pp.193] and [1, p.5] Efficiency concerns the ....
....nodes c 2 C. 2 Case based systems with attribute vectors often use a similarity measure which is computed as the weighted sum of attribute similarities ( composite similarities ) Such similarities can be easily implemented by special BCRNs (cf. Section 4 and [2, 7] As experiments show (cf. [5]) the implementation of case retrieval using CRNs is efficient. Moreover, B)CRNs offer the possibilities of extensions in various ways, some of which will be given now. q q q q q q q A1 A2 q q q q q q q q q A3 q q q q q q q q q A4 A2 q q q q q q q q q q q A4 q q q q q q q q q A1 A2 q q q q ....
[Article contains additional citation context not shown here]
M. Lenz. Case Retrieval Nets applied to large case bases. In H.-D. Burkhard and M. Lenz, editors, 4th German Workshop on CBR --- System Development and Evaluation, Berlin, 1996. Humboldt University.
....relevance. 3.3 Case Memory and Retrieval A crucial point in the RoboCup domain is that all players have to react in real time. Consequently, there is an urgent need for a highly efficient memory organization and retrieval procedure. For this reason, we applied the Case Retrieval Net (CRN) model [3, 4]. Figure 2 briefly sketches how the spreading activation mechanism of CRNs is used to determine the similarity of cases describing previously observed situations. The upper two pictures (A and B) show cases in the case base. Circles denote segments occupied by some other player; the position of ....
M. Lenz. Case Retrieval Nets applied to large case bases. In: Burkhard and Lenz (eds.): 4th German Workshop on CBR, 1996.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC