David Leake - Academia.edu (original) (raw)

Papers by David Leake

The success of case-based reasoning depends on effective retrieval of relevant prior cases. If re... more The success of case-based reasoning depends on effective retrieval of relevant prior cases. If retrieval is expensive, or if the cases retrieved are inappropriate, retrieval and adaptation costs will nullify many of the advantages of reasoning from prior experience. We propose an indexing vocabulary to facilitate retrieval of explanations in a casebased explanation system. The explanations we consider are explanations of anomalies (conflicts between new situations and prior expectations or beliefs). Our vocabulary groups anomalies according to the type of information used to generate the expectations or beliefs that failed, and according to how the expectations failed. We argue that by using this vocabulary to characterize anomalies, and retrieving explanations that were built to account for similarly-characterized past anomalies, a case-based explanation system can restrict retrieval to explanations likely to be relevant. In addition, the vocabulary can be used to organize general ...

ArXiv, 2021

The case difference heuristic (CDH) approach is a knowledge-light method for learning case adapta... more The case difference heuristic (CDH) approach is a knowledge-light method for learning case adaptation knowledge from the case base of a case-based reasoning system. Given a pair of cases, the CDH approach attributes the difference in their solutions to the difference in the problems they solve, and generates adaptation rules to adjust solutions accordingly when a retrieved case and new query have similar problem differences. As an alternative to learning adaptation rules, several researchers have applied neural networks to learn to predict solution differences from problem differences. Previous work on such approaches has assumed that the feature set describing problems is predefined. This paper investigates a two-phase process combining deep learning for feature extraction and neural network based adaptation learning from extracted features. Its performance is demonstrated in a regression task on an image data: predicting age given the image of a face. Results show that the combine...

Learning, goals, and learning goals, Ashwin Ram and David B. Leake. Part 1 Current state of the f... more Learning, goals, and learning goals, Ashwin Ram and David B. Leake. Part 1 Current state of the field: planning to learn, Lawrence Hunter quantitative results concerning the utility of explanation-based learning, Steven Minton the use of explicit goals for knowledge to guide inference and learning, Ashwin Ram and Lawrence Hunter deriving categories to achieve goals, Lawrence W. Barsalou harpoons and long sticks - the interaction of theory and similarity in rule induction, Edward J. Wisniewski and Douglas L. Medlin introspective reasoning using meta-explanations for multistrategy learning, Ashwin Ram and Michael T. Cox goal-directed learning - a decision-theoretic model for deciding what to learn next, Marie desJardins goal-based explanation evaluation, David B. Leake planning to perceive, Louise Pryor and Gregg Collins planning and learning in PRODIGY - overview of an integrated architecture, Jaime Carbonell et al a learning model for the selection of problem-solving strategies in c...

Goal-Driven Learning, 1995

Ai Magazine, Dec 15, 2007

In the mid to late 1980s there was a flurry of papers using explanationbased techniques to learn ... more In the mid to late 1980s there was a flurry of papers using explanationbased techniques to learn how to perform complex actions by observing (or interpreting descriptions of) human performance. These techniques were shown to work reasonably well with one or a small number of examples. However, as statistical approaches gained in power and popularity, and some kinds of data became more plentiful, machine learning as a field moved away from this kind of learning, which requires strong domain Reports

Lecture Notes in Computer Science, 1995

Abstract. A significant problem for case-based reasoning (CBR) systems is de-termining the featur... more Abstract. A significant problem for case-based reasoning (CBR) systems is de-termining the features to use in judging case similarity for retrieval. We describe research that addresses the feature selection problem by using introspective rea-soning to learn new features for ...

Lecture Notes in Computer Science, 2006

AAAI maintains compilation copyright for this technical report and retains the right of first ref... more AAAI maintains compilation copyright for this technical report and retains the right of first refusal to any publication (including electronic distribution) arising from this AAAI event. Please do not make any inquiries or arrangements for hardcopy or electronic publication of all or part of the papers contained in these working notes without first exploring the options available through AAAI Press and AI Magazine (concurrent submission to AAAI and an another publisher is not acceptable). A signed release of this right by AAAI is required before publication by a third party. Distribution of this technical report by any means including electronic (including, but not limited to the posting of the papers on any Website) without permission is prohibited.

Knowledge-Based Systems, 2014

The construction, capture and sharing of human knowledge is one of the fundamental problems of hu... more The construction, capture and sharing of human knowledge is one of the fundamental problems of human-centered computing. Electronic concept maps have proven to be a useful vehicle for building knowledge models. However, the user has to deal with the difficult task of deciding what information to include in these models. This article reports the culmination of a multi-year research project aimed at developing intelligent suggesters designed to aid users of concept mapping tools as they build their knowledge models. It describes DISCERNER and EXTENDER, two proactive suggesters that can be incorporated into the CmapTools concepts mapping system. DISCERNER applies case-based reasoning techniques to suggest potentially useful propositions mined from other users' knowledge models, while EXTENDER mines search engines to suggest new related areas to model. The article presents experimental results addressing two previously open questions for the project: DISCERNER'S retrieval accuracy and EXTENDER'S ability to generate artificial topics with content similar to topics determined by domain experts. Both experiments show satisfactory results.

The Knowledge Engineering Review, 2005

Case-based reasoning (CBR) is an approach to problem solving that emphasizes the role of prior ex... more Case-based reasoning (CBR) is an approach to problem solving that emphasizes the role of prior experience during future problem solving (i.e., new problems are solved by reusing and if necessary adapting the solutions to similar problems that were solved in the past). It has enjoyed considerable success in a wide variety of problem solving tasks and domains. Following a brief overview of the traditional problem-solving cycle in CBR, we examine the cognitive science foundations of CBR and its relationship to analogical reasoning. We then review a representative selection of CBR research in the past few decades on aspects of retrieval, reuse, revision and retention.

Artificial Intelligence, 1989

Explanation-based learning (EBL) is a very powerful method for category formation. Since EBL algo... more Explanation-based learning (EBL) is a very powerful method for category formation. Since EBL algorithms depend on having good explanations, it is crucial to have effective ways to build explanations, especially in complex real-world situations where complete causal information is not available. When people encounter new situations, they often explain them by remembering old explanations, and adapting them to fit. We believe that this case-based approach to explanation holds promise for use in AI systems, both for routine explanation and to creatively explain situations quite unlike what the system has encountered before. Building new explanations from old ones relies on having explanations available in memory. We describe explanation patterns (XPs), knowledge structures that package the reasoning underlying explanations. Using the SWALE system as a base, we discuss the retrieval and modification process, and the criteria used when deciding which explanation to accept. We also discuss issues in learning XPs: what generalization strategies are appropriate for real-world explanations, and which indexing strategies are appropriate for XPs. SWALE' s explanations allow it to understand nonstandard stories, and the XPs it learns increase its efficiency in dealing with similar anomalies in the future.

Guiding the generation of abductive explanations is a di cult problem. Applying casebased reasoni... more Guiding the generation of abductive explanations is a di cult problem. Applying casebased reasoning to abductive explanation generation|generating new explanations by retrieving and adapting explanations for prior episodes|o ers the bene t of re-using successful explanatory reasoning but raises new issues concerning how to perform similarity assessment to judge the relevance of prior explanations to new situations. Similarity assessment a ects two points in the case-based explanation process: deciding which explanations to retrieve and evaluating the retrieved candidates. We address the problem of identifying similar explanations to retrieve by basing that similarity assessment on a categorization of anomaly types. We show that the problem of evaluating retrieved candidate explanations is often impeded by incomplete information about the situation to be explained, and address that problem with a novel similarity assessment method which we call constructive similarity assessment. Constructive similarity assessment contrasts with traditional \feature-mapping" similarity assessment methods by using the contents of memory to hypothesize important features in the new situation, and in using a pragmatic criterion|the system's ability to adapt features of the old case into features that apply in the new circumstances|as the basis for comparing features. Thus constructive similarity assessment does not merely compare new cases to old; instead, based on adaptation of prior cases in memory, it addresses the problem of incomplete input cases by building up and reasoning about augmented descriptions of those cases.

The case-based reasoning CBR process solves problems by retrieving prior solutions and adapting t... more The case-based reasoning CBR process solves problems by retrieving prior solutions and adapting them to t new circumstances. Many studies examine how casebased reasoners learn by storing new cases and re ning the indices used to retrieve cases. However, little attention has been given to learning to re ne the process for applying retrieved cases. This paper describes research investigating how a case-based reasoner can learn strategies for adapting prior cases to t new situations, and how its similarity criteria may be re ned pragmatically to re ect new capabilities for case adaptation. We b e g i n by highlighting psychological research on the development of similarity criteria and summarizing our model of case adaptation learning. We then discuss initial steps towards pragmatically re ning similarity criteria based on experiences with case adaptation.

One application of models of reasoning behavior is to allow a reasoner to introspectively detect ... more One application of models of reasoning behavior is to allow a reasoner to introspectively detect and repair failures of its own reasoning process. We address the issues of the transferability of such models versus the specificity of the knowledge in them, the kinds of knowledge needed for self-modeling and how that knowledge is structured, and the evaluation of introspective reasoning systems. We present the ROBBIE system which implements a model of its planning processes to improve the planner in response to reasoning failures. We show how ROBBIE's hierarchical model balances model generality with access to implementation-specific details, and discuss the qualitative and quantitative measures we have used for evaluating its introspective component.