Bimbaum, L., Collins, G., Brand, M., Freed, M., Krulwich, B., Pryor, L. (1989) A Model-Based Approach to the Construction of Adaptive Case-Based Planning Systems. Proceedings of the Case-Based Reasoning Workshop, Florida, USA.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....that easily adapted matches should be preferred over hard to adapt matches. Goel s KRITIK system [2] also prefers candidate design cases that satisfy the functional specifications of the target design and hence have easilyadaptable matches. Bimbaum, Collins, Brand, Freed, Krulwich Pryor [3] proposed a system that learns to index cases on the basis of their adaptability, overriding semantic similarity where appropriate, a proposal that has been implemented by Fox Leake [4] Their system avoids cases with feature combinations that were difficult to adapt in previous problem solving ....

Bimbaum, L., Collins, G., Brand, M., Freed, M., Krulwich, B., Pryor, L. (1989) A Model-Based Approach to the Construction of Adaptive Case-Based Planning Systems. Proceedings of the Case-Based Reasoning Workshop, Florida, USA.

....in it being preferred over other matches which are indicative of more difficult adaptations. Similarly, in KRITIK Goel [3] favours candidate design cases that are easier to adapt by preferring matches which satisfy the functional specifications of the desired, target design. Birnbaum et al. [14] propose a system that learns to index cases on the basis of their adaptability, overriding semantic similarity where appropriate. During problem solving certain feature combinations are identified as particularly problematic and cases with such features can be avoided in future problem solving ....

Birnbaum, L., Collins, G., Brand, M., Freed, M., Krulwich, B., and Pryor, L. A Model- Based Approach to the Construction of Adaptive Case-Based Planning Systems. Proceedings of the Case-Based Reasoning Workshop, pp 191-198, Morgan Kaufmann, 1988.

....topology in the case space. We argue that the approximation of this topology, i.e. its metrization, is the general framework in which to face the problem of adaptation driven retrieval. 1 Introduction Both case retrieval and case adaptation are central features of CBR systems. Several authors [3, 4, 6, 8, 1] had proposed to enhance the effectiveness of the retrieval procedure with information about the kind of adaptation that the system provides. The working hypothesis is quite intuitive (see [2] an easy to adapt case is preferable to a even more similar case if the adaptation is too expensive. ....

L. Birnbaum, G. Collins, M. Brand, M. Freed, B. Krulwich, and L. Pryor. A modelbased approach to the construction of adaptive case-based planning systems. In I. Bareiss, Ray; Lewis, Sharon; Gravitis, editor, Proceedings of a Workshop on CaseBased Reasoning, pages 215--224, Washington, D.C., May 1991. Morgan Kaufmann.

....that easily adapted matches should be preferred over hard to adapt matches. Goel s KRITIK system [2] also prefers candidate design cases that satisfy the functional specifications of the target design and hence have easily adaptable matches. Birnbaum, Collins, Brand, Freed, Krulwich Pryor [3] proposed a system that learns to index cases on the basis of their adaptability, overriding semantic similarity where appropriate, a proposal that has been implemented by Fox Leake [4] Their system avoids cases with feature combinations that were difficult to adapt in previous problem solving ....

Birnbaum, L., Collins, G., Brand, M., Freed, M., Krulwich, B., Pryor, L. (1989) A Model-Based Approach to the Construction of Adaptive CaseBased Planning Systems. Proceedings of the Case-Based Reasoning Workshop, Florida, USA.

.... (Smyth Keane, 1994) Furthermore, AGR works without incurring the full cost of adaptation during retrieval (in section 5 we show that it can even be more efficient than conventional methods) The idea that retrieval should be sensitive to adaptation requirements has been mooted before (see Birnbaum et al. 1989; Fox Leake, 1995; Goel, 1989; Keane, 1993; Kolodner, 1989; Leake, 1992) Kolodner (1989) argues that some classes of matches, easily adapted matches, should be preferred over hard to adapt matches during retrieval. Similarly, Goel s KRITIK system (Goel, 1989) prefers candidate ....

....some classes of matches, easily adapted matches, should be preferred over hard to adapt matches during retrieval. Similarly, Goel s KRITIK system (Goel, 1989) prefers candidate design cases that satisfy the functional specifications of the target design and hence have easily adaptable matches. Birnbaum, et al. 1989) proposed a system that learns to index cases on the basis of their adaptability, overriding semantic similarity where appropriate and Fox Leake (1995) have implemented just such a system. The difference between these techniques and adaptation guided retrieval is that they all involve an ....

Birnbaum, L., Collins, G., Brand, M., Freed, M., Krulwich, B., Pryor, L. 1989. A Model-Based Approach to the Construction of Adaptive Case-Based Planning Systems. In Proceedings of the CaseBased Reasoning Workshop, 215-224, Florida, USA.

....VU (Smyth Keane 1995) where adaptability is assessed based on specially formulated adaptation knowledge, and is used to guide retrieval. Huang and Miles (Huang Miles 1995) calculate the conflict propagation potential of a case to assess ease of adaptation during retrieval. Birnbaum et al. L. Birnbaum 1989) and Leake Fox (Leake Fox 1992) index cases on the basis of their adaptability, avoiding cases with feature combinations that were difficult to adapt in previous problem solving episodes. Portinale et al. L. Portinale Magro 1997) describe a technique called Pivoting Based Retrieval, in ....

L. Birnbaum, G. Collins, M. B. e. a. 1989. A modelbased approach to the construction of adaptive casebased planning systems. In Proceedings of the Case Based Reasoning Workshop, Florida, USA.

....of user adaptations are stored as adaptation cases for reuse by derivational analogy. 5. Similarity learning: When a case based reasoning system performs similarity assessment to determine which case is most similar to a new situation, the goal is to select the case that will be easiest to adapt (Birnbaum et al. 1991; Leake 1995a; Smyth Keane 1995) DIAL s similarity assessment process uses prior experiences with case adaptation to estimate case adaptation cost for new problems, by a transformational analogy process. Consequently, adaptation learning and similarity learning are coupled: when adaptation ....

Birnbaum, L.; Collins, G.; Brand, M.; Freed, M.; Krulwich, B.; and Pryor, L. 1991. A model-based approach to the construction of adaptive case-based planning systems. In Bareiss, R., ed., Proceedings of the DARPA Case-Based Reasoning Workshop, 215-- 224. San Mateo: Morgan Kaufmann.

....individual actions of the simulated robot. 3 The Introspective Reasoning Task ROBBIE s high level task is to improve its reasoning process when reasoning failures are detected. ROBBIE s approach uses a declarative model describing the underlying system s reasoning processes (Fox Leake, 1994; Birnbaum et al. 1991; Freed Collins, 1994) The model contains assertions about the system s ideal reasoning behavior; the actual reasoning is compared to this ideal to detect discrepancies which are viewed as reasoning failures. Once a reasoning failure is detected the model is used to create an explanation of the ....

Birnbaum, L., Collins, G., Brand, M., Freed, M., Krulwich, B., & Pryor, L. (1991). A model-based approach to the construction of adaptive case-based planning systems.

....robot to execute. 3.2 The Introspective Task The higher level task for ROBBIE is to improve its reasoning processes in response to detected reasoning failures. ROBBIE s approach uses an explicit, declarative model describing the underlying system s reasoning processes [ Fox and Leake, 1994; Birnbaum et al. 1991; Freed and Collins, 1994 ] The model provides expectations about the ideal reasoning behavior of the system; the actual reasoning of the system is compared to this ideal as a means of detecting reasoning failures. Once a reasoning failure is detected the model is used to create an explanation ....

....highly promising. 4 6 Relationship to previous research There has been a significant amount of work in the past few years on methods for implementing introspective reasoning. Our work was inspired by the proposals for using model based reasoning to improve the performance of CBR systems made by [ Birnbaum et al. 1991 ] In a similar spirit, Freed implements an introspective model in RAPTER, a reactive planning system [ Freed and Collins, 1994 ] RAPTER focuses on analysis of the reasoning trace of the planner, using justification structures which trace the chain of assumptions made by the system used to ....

L. Birnbaum, G. Collins, M. Brand, M. Freed, B. Krulwich, and L. Pryor. A model-based approach to the construction of adaptive case-based planning systems. In R. Bareiss, editor, Proceedings of the Case-Based Reasoning Workshop, pages 215--224, San Mateo, 1991. DARPA, Morgan Kaufmann, Inc.

....discrepancies. A discrepancy indicates a reasoning failure; the failure is corrected by explaining why it occurred and revising the reasoning process to avoid future failures. Using introspective learning to improve the case based reasoning process itself was first suggested by Birnbaum et al. [6]. Introspective improvement of reasoning processes is a relatively new approach, and there have been few evaluations of its effect on the performance of a system using it. We designed empirical tests to examine the effect of introspective learning on ROBBIE s performance, and to examine the effect ....

....reasoning process (in particular, its feature selection process) when it detects failures in its reasoning. As the planner reasons about its task, the introspective component monitors its reasoning process by comparing it to a declarative model describing the planner s ideal reasoning processes [6, 9, 12]. Reasoning failures occur when the model s expectations about the reasoning process are not fulfilled by the actual reasoning. Expectations are encoded as assertions; facts that would be ideally true of particular points in the case based reasoning process. For example, one assertion states ....

[Article contains additional citation context not shown here]

L. Birnbaum, G. Collins, M. Brand, M. Freed, B. Krulwich, and L. Pryor. A model-based approach to the construction of adaptive case-based planning systems. In R. Bareiss, editor, Proceedings of the Case-Based Reasoning Workshop, pages 215--224, San Mateo, 1991. DARPA, Morgan Kaufmann, Inc.

....(adaptation learning) Leake et al. 1996 ] We hypothesized that the problem might be caused by a mismatch between the system s similarity assessment criteria and the system s changing case adaptation abilities. To facilitate adaptation, similarity criteria should reflect adaptability [ Birnbaum et al. 1991; Leake, 1992a; Smyth and Keane, 1996 ] Thus when new adaptations are learned, similarity criteria should be modified to reflect changed adaptation abilities, in order to select the cases that will be easiest to adapt. However, early versions of DIAL like most other CBR systems relied on ....

L. Birnbaum, G. Collins, M. Brand, M. Freed, B. Krulwich, and L. Pryor. A modelbased approach to the construction of adaptive casebased planning systems. In R. Bareiss, editor, Proceedings of the DARPA Case-Based Reasoning Workshop, pages 215--224, San Mateo, 1991. Morgan Kaufmann.

....search process for the needed information. Memory search as a planful process Our approach builds on the model of memory traversal and index elaboration in CYRUS (Kolodner, 1984) and especially on prior proposals for introspective failure driven learning to repair memory organization problems (Birnbaum, Collins, Brand, Freed, Krulwich, Pryor, 1991; Ram Cox, 1994) However, this model differs in treating memory search as a knowledge planning process (Hunter, 1990) In the knowledge planning framework, information search is conducted by a planning process based on explicit reasoning about needs for information and how to satisfy them. In ....

Birnbaum, L., Collins, G., Brand, M., Freed, M., Krulwich, B., & Pryor, L. (1991). A model-based approach to the construction of adaptive case-based planning systems.

....nal reasoning process, for similarity assessment. As has been pointed out by a number of researchers, the goal of similarity assessment in CBR is to select the prior cases that can be most easily applied to the new situation. As a result, useful similarity judgments must reflect adaptability (Birnbaum et al. 1991; Leake 1992; Smyth Keane 1996) Because DIAL s rule based case adaptation is augmented with case based adaptation, which enables learning how to perform adaptations, adaptability of cases changes with adaptation learning so similarity judgments must change as well. This led us to investigate ....

Birnbaum, L.; Collins, G.; Brand, M.; Freed, M.; Krulwich, B.; and Pryor, L. 1991. A model-based approach to the construction of adaptive case-based planning systems. In Bareiss, R., ed., Proceedings of the DARPA Case-Based Reasoning Workshop, 215-- 224. San Mateo: Morgan Kaufmann.

....for extending the model based reasoning process to perform introspective reasoning about all parts of the CBR system. Developing and applying a multi level model Determining what information to include in the model, and how to structure it, are central issues. In Birnbaum et al. s proposal (Birnbaum et al. 1991), the model of CBR contains very high level assertions applicable to the broad class of casebased planners. While such assertions cover a wide range of failures, they are not operational for identifying appropriate repairs for failures. We are developing a hierarchical model spanning the spectrum ....

Birnbaum, L., Collins, G., Brand, M., Freed, M., Krulwich, B., & Pryor, L. (1991). A model-based approach to the construction of adaptive case-based planning systems. In Bareiss, R.

.... 1995; Branting Porter, 1991; Koton, 1988; Goel, 1989; Golding Rosenbloom, 1991; Portinale Torasso, 1995; Skalak Rissland, 1991) Metareasoning about system performance, based on a self model, can be used to guide learning to refine the CBR process itself (e.g. Arcos Plaza, 1994; Birnbaum et al. 1991; Fox, 1995; Fox Leake, 1995a, 1995b, 1995c; Leake, Kinley, and Wilson, Chapter 11; Ram Cox, 1994) CBR may be also be applied in a fully integrated framework that performs strategic reasoning about each processing step (e.g. Aamodt, 1994; Armengol Plaza, 1994) In this volume, Veloso ....

Birnbaum, L.; Collins, G.; Brand, M.; Freed, M.; Krulwich, B.; and Pryor, L. 1991. A modelbased approach to the construction of adaptive case-based planning systems. In Bareiss, R., ed., Proceedings of the DARPA Case-Based Reasoning Workshop, 215--224. San Mateo: Morgan Kaufmann.

.... be achieved through plans based on reasoning about the system s information seeking abilities [ Hunter, 1990; Pryor and Collins, 1991 ] The planful memory search framework requires the additional development of an internal model that the CBR system can use to reason about its own processing [ Birnbaum et al. 1991 ] In particular, a model is needed for the system s own memory search process. Two types of knowledge are required for a suitable memory model: 1) abstract domain independent knowledge about the structure of the memory (e.g. that abstractions of a concept can be obtained by following ....

....models of failure driven plan repair should be readily applicable to this task, one new issue that arises is how to detect the memory search problems themselves. The issue here is one of identifying and diagnosing failures of the system s own internal processing (e.g. Birnbaum et al. 1990; Birnbaum et al. 1991 ] To be able to recognize failures of adaptation strategies, the system must be able to detect memory search failures such as: ffl The search plan cannot be completed (e.g. due to failure to find intermediate information) ffl The search plan can be completed, but no specific information is ....

[Article contains additional citation context not shown here]

Birnbaum, L.; Collins, G.; Brand, M.; Freed, M.; Krulwich, B.; and Pryor, L. 1991. A model-based approach to the construction of adaptive case-based planning systems.

....studies showed that learning adaptation cases improved adaptation performance (Leake et al. 1996) but the method also raised questions about how to refine similarity assessment as adaptation cases are acquired. The difficulty is that useful similarity judgments must reflect adaptability (Birnbaum et al. 1991; Smyth and Keane, 1996) In a case based adaptation system, adaptability is not static it changes as adaptation cases are learned. Consequently, similarity judgments much change as well. This led us to investigate extending our system s internal case based methods to use adaptation cases for ....

.... 5 A case based framework for similarity learning Previous work on refining similarity criteria to match adaptation abilities focuses primarily on adjusting a set of similarity criteria (that approximate adaptability) rather than judging adaptability directly from adaptation knowledge (Birnbaum et al. 1991). Research by Smyth and Keane (1996) takes a valuable step in replacing semantic similarity with adaptability, but does not address learning: Their method assumes adaptation knowledge is static and depends on adaptation rules being annotated with estimated costs by the system designer. In ....

L. Birnbaum, G. Collins, M. Brand, M. Freed, B. Krulwich, and L. Pryor. A model-based approach to the construction of adaptive case-based planning systems. In R. Bareiss, editor, Proceedings of the DARPA Case-Based Reasoning Workshop, pages 215--224, San Mateo, 1991. Morgan Kaufmann.

....new situation and how to adapt them to fit new circumstances. Although CBR systems often base similarity judgments on semantic similarity, the real goal of similarity assessment in CBR is to determine adaptability: how easily an old case can be adapted to fit the requirements of a new situation (Birnbaum et al. 1991; Smyth and Keane, 1995, 1996) If adaptation knowledge is learned, static similarity criteria may not keep pace with new capabilities for performing adaptations. Thus similarity assessment criteria should change as new adaptation knowledge is acquired. We first discuss the relationship of our ....

Birnbaum, L., Collins, G., Brand, M., Freed, M., Krulwich, B., and Pryor, L. (1991). A model-based approach to the construction of adaptive case-based planning systems. In Bareiss, R., editor, Proceedings of the DARPA Case-Based Reasoning Workshop, pages 215--224, San Mateo. Morgan Kaufmann.

....CBR process itself to detect processing failures: Modelbased reasoning is a widely studied method for diagnosing device failures (for an overview, see Davis (1988) In that work, faults are identified by comparing a model of how the device is expected to perform to the device s actual behavior. Birnbaum, Collins, Freed and Krulwich (1991) point out that model based reasoning can also be used in a different way: Rather than having the model reflect the expected behavior of a system, they suggest using a model of the ideal behavior of a reasoning system behavior that may be beyond expectations for actual performance as a ....

....a benchmark against which to compare actual system performance. Discrepancies identify points for improvement. Although Birnbaum et al. applied the method to the task of refining a rule based planning system, they proposed its application to self improving case based reasoning systems as well (Birnbaum et al. 1991). The remainder of this section discusses the application of that method to refining indexing criteria in a case based path planning system (Fox Leake, 1994, 1995b, 1995c, 1995a) By this process, the system acquires expertise at case retrieval. Identifying hidden retrieval problems by ....

Birnbaum, L., Collins, G., Brand, M., Freed, M., Krulwich, B., & Pryor, L. (1991). A model-based approach to the construction of adaptive case-based planning systems.

....case based planning component as a set of expectations about the behavior of the system during the planning process. ROBBIE monitors the reasoning of its underlying system, comparing its performance to a model of the ideal performance of the case based reasoning process, as first proposed by Birnbaum et al. 1991). The model contains expectations about each portion of the system s reasoning processes. These expectations, assertions that would hold for an ideal CBR system, are organized by the component of the system they refer to, their level of specificity, and their relations to other expectations. The ....

.... 1986; Kolodner, 1993) combined with a simple reactive style execution system (Firby, 1989) Overarching the performance task is the task of learning introspectively about the planning and execution process itself, which is done using model based reasoning about the system s own reasoning process (Birnbaum et al. 1991; Collins, Birnbaum, Krulwich, Freed, 1993; Birnbaum, Collins, Freed, Krulwich, 1990) This higher level task is performed by a separate component which interacts with the planner (see Figure 1) Presented with a starting location (usually the current location of the simulated robot) and a ....

[Article contains additional citation context not shown here]

Birnbaum, L., Collins, G., Brand, M., Freed, M., Krulwich, B., & Pryor, L. (1991). A model-based approach to the construction of adaptive case-based planning systems.

....be fixed ahead of time by the designer. This assumption may break down in complex domains. The focus of this research is developing a model of introspective reasoning and learning to enable a system to improve its own reasoning as well as its domain knowledge. Our model is based on the proposal of (Birnbaum et al. 1991) to use a model of the ideal behavior of a case based system to judge system performance and to refine its reasoning mechanisms; it also draws on the research of (Ram Cox 1994) on introspective failure driven learning. This work examines introspection guided by expectation failures about ....

....In this case our system creates a new index to distinguish the true best case from the bad retrieved case. Determining what information to include in the model and how to structure it are central issues. Birnbaum s model is a set of high level assertions applicable to many case based planners (Birnbaum et al. 1991). While such assertions cover a wide range of failures, they are too general to easily specify causes or repairs for failures. We propose as an alternative a hierarchical model including highly abstract assertions as well as assertions specific to this planner. Low level assertions help to notice ....

Birnbaum, L.; Collins, G.; Brand, M.; Freed, M.; Krulwich, B.; and Pryor, L. 1991. A model-based approach to the construction of adaptive case-based planning systems. In Proceedings of the DARPA CBR Workshop, 215--224. Morgan Kaufman.

No context found.

Birnbaum, L., Collins, G., Brand, M., Freed, M., Krulwich, B., and Prior, L. (1991) A ModelBased Approach to the Construction of Adaptive Case-Based Planning Systems. Proceedings of the Case-Based Reasoning Workshop, pp. 215-224. Washington D.C., USA.

No context found.

Florida, U.S.A. Birnbaum, L., Collins, G., Brand, M., Freed, M., Krulwich, B., Pryor, L. (1989) A Model-Based Approach to the Construction of Adaptive Case-Based Planning Systems. Proceedings of the Case-Based Reasoning Workshop, (pp.

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