Case-based prediction (CBP) methods do not learn a model of the target decision function but instead perform an inference process that depends on two similarity measures and a reference case base. This paper proposes a strategy, called EnergyCompress, to learn an effective case base by selecting relevant cases from an initial set. Use of EnergyCompress decreases CBP inference time, through case base compression, and also increases prediction performance, for a wide variety of CBP algorithms. EnergyCompress relies on the proposition of a general formulation of the CBP task in the framework of energy-based models, which leads to a new and valuable characterization of the notion of competence in case-based reasoning, in particular at the source case level. Extensive experimental results on 18 benchmark datasets comparing EnergyCompress to 5 reference algorithms for case base maintenance support the benefit of the proposed strategy.

Deep neural networks have achieved remarkable performance across a variety of applications. However, their decision-making processes are opaque. In contrast, k-nearest neighbor (k-NN) provides interpretable predictions by relying on similar cases, but it lacks important capabilities of neural networks. The neural network k-nearest neighbor (NN-kNN) model is designed to bridge this gap, combining the benefits of neural networks with the instance-based interpretability of k-NN. However, the initial formulation of NN-kNN had limitations including scalability issues, reliance on surface-level features, and an excessive number of parameters. This paper improves NN-kNN by enhancing its scalability, parameter efficiency, ease of integration with feature extractors, and training simplicity. An evaluation of the revised architecture for image and language classification tasks illustrates its promise as a flexible and interpretable method.

This paper presents ENHAnCE, an algorithm that simultaneously learns a predictive model of the input stream and generates representations of the concepts being observed. Following cognitively-inspired models of event segmentation, ENHAnCE uses expectation violations to identify boundaries between temporally extended patterns. It applies its expectation-driven process at multiple levels of temporal granularity to produce a hierarchy of predictive models that enable it to identify concepts at multiple levels of temporal abstraction. Evaluations show that the temporal abstraction hierarchies generated by ENHAnCE closely match hand-coded hierarchies for the test data streams. Given language data streams, ENHAnCE learns a hierarchy of predictive models that capture basic units of both spoken and written language: morphemes, lexemes, phonemes, syllables, and words.

The ability of case-based reasoning systems to solve novel problems depends on their capability to adapt past solutions to new circumstances. However, acquiring the knowledge required for case adaptation is a classic challenge for CBR. This motivates the use of machine learning methods to generate adaptation knowledge. A popular approach uses the case difference heuristic (CDH) to generate adaptation rules from pairs of cases in the case base, based on the premise that the observed differences in case solutions result from the differences in the problems they solve, so can form the basic of rules to adapt cases with similar problem differences. Extensive research has successfully applied the CDH approach to adaptation rule learning for case-based regression (numerical prediction) tasks. However, classification tasks have been outside of its scope. The work presented in this paper addresses that gap by extending CDH-based learning of adaptation rules to apply to cases with categorical features and solutions. It presents the generalized case value heuristic to assess case and solution differences and applies it in an ensemble-based case-based classification method, ensembles of adaptations for classification (EAC), built on the authors' previous work on ensembles of adaptations for regression (EAR). Experimental results support the effectiveness of EAC.

Identifying the social closeness between two individuals is a key skill in any situation where interpersonal relations play a role. Consequently, such capacity is needed to enable AI systems to understand human interactions and interact naturally in social situations. However, current research has relied on simple proxies for social closeness, and richer models are difficult to achieve. This paper presents an approach to predicting social closeness based on linguistic interactions and demonstrates an ability to predict social closeness with high accuracy.

Electronic concept maps, interlinked with other concept maps and multimedia resources, can provide rich knowledge models to capture and share human knowledge. This article presents and evaluates methods to support experts as they extend existing knowledge models, by suggesting new context-relevant topics mined from Web search engines. The task of generating topics to support knowledge model extension raises two research questions: first, how to extract topic descriptors and discriminators from concept maps; and second, how to use these topic descriptors and discriminators to identify candidate topics on the Web with the right balance of novelty and relevance. To address these questions, this article first develops the theoretical framework required for a “topic suggester” to aid information search in the context of a knowledge model under construction. It then presents and evaluates algorithms based on this framework and applied in E xtender , an implemented tool for topic suggestion. E xtender has been developed and tested within CmapTools, a widely used system for supporting knowledge modeling using concept maps. However, the generality of the algorithms makes them applicable to a broad class of knowledge modeling systems, and to Web search in general.

Transfer learning is typically performed between problem instances within the same domain. We consider the problem of transferring across domains. To this effect, we adopt a probabilistic logic approach. First, our approach automatically identifies predicates in the target domain that are similar in their relational structure to predicates in the source domain. Second, it transfers the logic rules and learns the parameters of the transferred rules using target data. Finally, it refines the rules as necessary using theory refinement. Our experimental evidence supports that this transfer method finds models as good or better than those found with state-of-the-art methods, with and without transfer, and in a fraction of the time.

In case-based reasoning (CBR), problems are solved by retrieving prior cases and adapting their solutions to fit; learning occurs as new cases are stored. Controlling the growth of the case base is a fundamental problem, and research on case-base maintenance has developed methods for compacting case bases while maintaining system competence, primarily by competence-based deletion strategies assuming static case adaptation knowledge. This paper proposes adaptation-guided case-base maintenance (AGCBM), a case-base maintenance approach exploiting the ability to dynamically generate new adaptation knowledge from cases. In AGCBM, case retention decisions are based both on cases' value as base cases for solving problems and on their value for generating new adaptation rules. he paper illustrates the method for numerical prediction tasks (case-based regression) in which adaptation rules are generated automatically using the case difference heuristic. In comparisons of AGCBM to five alternative methods in four domains, for varying case base densities, AGCBM outperformed the alternatives in all domains, with greatest benefit at high compression.

Scientific discovery increasingly requires collaboration between scientific sub-domains that often have different representations for their data. To bridge gaps between varying domain representations, researchers are developing metadata and semantic representations meaningful to broader communities. Through exploiting these representations we propose a logical model and architecture by which cross-domain researchers can more easily discover, use, and eventually archive, data. In this paper we present an architecture, intermediate data model, and methodology for mapping diverse social-ecological data sources stored in relational databases to a common representation, and for classifying textual data using machine learning. The results are visualized through client views that are built against the general logical model, and applied against a longitudinal database from social-ecological research.

Much intelligent user interfaces research addresses the problem of providing information relevant to a current user topic. However, little work addresses the complementary question of helping the user identify potential topics to explore next. In knowledge acquisition, this question is crucial to deciding how to extend previously-captured knowledge. This paper examines requirements for effective topic suggestion and presents a domain-independent topic-generation algorithm designed to generate candidate topics that are novel but related to the current context. The algorithm iteratively performs a cycle of topic formation, Web search for connected material, and context-based filtering. An experimental study shows that this approach significantly outperforms a baseline at developing new topics similar to those chosen by an expert for a hand-coded knowledge model.

Effective knowledge management may require going beyond initial knowledge capture, to support decisions about how to extend previously-captured knowledge. Electronic concept maps, interlinked with other concept maps and multimedia resources, can provide rich knowledge models for human knowledge capture and sharing. This paper presents research on methods for supporting experts as they extend these knowledge models, by searching the Web for new context-relevant topics as candidates for inclusion. This topic search problem presents two challenges: First, how to formulate queries to seek topics that reflect the context of the current knowledge model, and, second, how to identify candidate topics with the right balance of novelty and relevance. More generally, this problem raises the broad question of the interaction of topic information from the local analysis space (a collected set of documents) and the global search space (the Web). The paper develops a framework for understanding this interaction, and proposes and evaluates techniques for addressing the query formation and topic identification questions by dynamically extracting topic descriptors and discriminators from a knowledge model, to characterize information needs for retrieval and filtering of relevant material. Using these techniques, we have developed a support tool that starts from a knowledge model under construction and automatically produces a set of suggestions for topics to include, proactively supporting users as they extend knowledge models.

Electronic concept mapping tools empower experts to play an active role in the knowledge capture process, and provide a medium for building richly connected multimedia knowledge models -- sets of linked concept maps and resources about a particular domain. Knowledge models are intended to be used as a means for sharing knowledge among humans, not as carefully-crafted knowledge bases upon which machines will be performing inference. However, users must still confront the questions of what to include in a concept map and which concept maps to include in a knowledge model. This paper describes ongoing research on methods to provide content-based support to users as they extend concept maps by adding concepts and propositions, and as they select topics for new maps. The goal is to provide scaffolding for experts as they build their own concept maps, link their maps to others', and decide how to extend their knowledge models. The paper presents three approaches which start from a concept map under construction and mine related information -- both from prior concept maps, and from the web -- to propose information to aid the user's knowledge capture and knowledge construction. The paper begins with a brief summary of the concept mapping process and the CmapTools concept mapping software. It then presents three types of implemented suggesters, to suggest concepts, propositions, concept maps, and new topics to aid experts using the CmapTools, and describes preliminary experiments to assess their performance. It closes with a discussion of next steps for testing and refining these methods.

In order for intelligent interfaces to provide proactive assistance, they must customize their behavior based on the user's task context. Existing systems often assess context based on a single snapshot of the user's current activities (e. g., examining the content of the document that the user is currently consulting). However, an accurate picture of the user's context may depend not only on this local information, but also on information about the user's behavior over time. This paper discusses work on a recommender system, Calvin, which learns to identify broader contexts by relating documents that tend to be accessed together. Calvin's text analysis algorithm, WordSieve, develops term vector descriptions of these contexts in real time, without needing to accumulate comprehensive statistics about an entire corpus. Calvin uses these descriptions (1) to index documents to suggest them in similar future contexts and (2) to formulate contextbased queries for search engines. Results of initial experiments are encouraging for the approach's improved ability to associate documents with the research tasks in which they were consulted, compared to methods using only local information. This paper sketches the project goals, the current implementation of the system, and plans for its continued development and evaluati.

The success of personal information agents depends on their ability to provide task-relevant information. This paper presents WordSieve, a new algorithm that generates context descriptions to guide document indexing and retrieval. WordSieve exploits information about the sequence of accessed documents to identify words which indicate a shift in context. We have tested WordSieve in a personal information agent, Calvin, which monitors a user's document access, generates a representation of the user's task context, indexes the resources consulted, and presents recommendations for other resources that were consulted in similar prior contexts. In initial experiments, WordSieve outperforms term frequency/inverse document frequency at matching documents to hand-coded vector representations of the task contexts in which they were originally consulted, where the task context representations are term vectors representing a specific search task given to the user.

Many case-based reasoning systems have been developed to aid designers by providing them with libraries of prior design experiences. Traditionally, these systems are implemented as stand-alone ``external memories'' for the designer to query manually. This paper presents a contrasting approach that integrates proactive case retrieval into the designer's normal task processes, automatically tailoring information selection and presentation emphasis to fit changing designer needs and attention flow. The paper presents a set of principles for this integrated intelligent design support and describes their application in the Stamping Advisor, a system to support design feasibility analysis for sheet metal automotive parts. The Stamping Advisor interface proactively provides designers with relevant information to support feasibility analysis, automatically prepares their information products, and unobtrusively gathers the information needed to generate new cases to improve the quality of future support.

A well-known problem for web search is targeting search on information that satis es users ' information needs. User queries tend to be short, and hence often ambiguous, which can lead to inappropriate results from general-purpose search engines. This has led to a number of methods for narrowing queries by adding information. This paper presents an alternative approach that aims to improve query results by using knowledge of a user's current activities to select search engines relevant totheir information needs, exploiting the proliferation of high-quality special-purpose search services. The paper introduces the prism source selection system and describes its approach. It then describes two initial experiments testing the system's methods.

Experience with the growing number of large‐scale and long‐term case‐based reasoning (CBR) applications has led to increasing recognition of the importance of maintaining existing CBR systems. Recent research has focused on case‐base maintenance (CBM), addressing such issues as maintaining consistency, preserving competence, and controlling case‐base growth. A set of dimensions for case‐base maintenance, proposed by Leake and Wilson, provides a framework for understanding and expanding CBM research. However, it also has been recognized that other knowledge containers can be equally important maintenance targets. Multiple researchers have addressed pieces of this more general maintenance problem, considering such issues as how to refine similarity criteria and adaptation knowledge. As with case‐base maintenance, a framework of dimensions for characterizing more general maintenance activity, within and across knowledge containers, is desirable to unify and understand the state of the art, as well as to suggest new avenues of exploration by identifying points along the dimensions that have not yet been studied. This article presents such a framework by (1) refining and updating the earlier framework of dimensions for case‐base maintenance, (2) applying the refined dimensions to the entire range of knowledge containers, and (3) extending the theory to include coordinated cross‐container maintenance. The result is a framework for understanding the general problem of case‐based reasoner maintenance (CBRM). Taking the new framework as a starting point, the article explores key issues for future CBRM research.

Introspective reasoning can enable a reasoner to learn by refining its own reasoning processes. In order to perform this learning, the system must monitor the course of its reasoning to detect learning opportunities and then apply appropriate learning strategies. This article describes lessons learned from research on a computer model of how introspective reasoning can guide failure-driven learning. The computer model monitors its own reasoning by comparing it to a model of the desired behaviour of its reasoning, and learns in response to deviations from the ideal defined by the model. The approach is applied to the problem of determining indices for selecting cases from a case-based planner's memory. Experiments show that learning driven by this introspective reasoning both decreases retrieval effort and improves the quality of plans retrieved, increasing the overall performance of the planning system compared to case learning alone.

The case-based reasoning paradigm models how reuse of stored experiences contributes to expertise. In a case-based problem-solver, new problems are solved by retrieving stored information about previous problem-solving episodes and adapting it to suggest solutions to the new problems. The results are then themselves added to the reasoner's memory in new cases for future use. Despite this emphasis on learning from experience, however, experience generally plays a minimal role in models of how the case-based reasoning process is itself performed. Case-based reasoning systems generally do not refine the methods they use to retrieve or adapt prior cases, instead relying on static pre-defined procedures. The thesis of this article is that learning from experience can play a key role in building expertise by refining the case-based reasoning process itself. To support that view and to illustrate the practicality of learning to refine case-based reasoning, this article presents ongoing research into using introspective reasoning about the case-based reasoning process to increase expertise at retrieving and adapting stored cases.

Many abductive understanding systems generate explanations by a backwards chaining process that is neutral both to the explainer's previous experience in similar situations and to why the explainer is attempting to explain. This article examines the relationship of such models to an approach that uses case-based reasoning to generate explanations. In this case-based model, the generation of abductive explanations is focused by prior experience and by goal-based criteria reflecting current information needs. The article analyses the commitments and contributions of this case-based model as applied to the task of building good explanations of anomalous events in everyday understanding. The article identifies six central issues for abductive explanation, compares how these issues are addressed in traditional and case-based explanation models, and discusses benefits of the case-based approach for facilitating generation of plausible and useful explanations in domains that are complex and imperfectly understood.

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.