Key words: machine learning, concept acquisition, explanation-based learning Abstract. In the last issue of this journal Mitchell, Keller, and Kedar-Cabelli presented a unifying framework for the explanation-based approach to machine learning. While it works well for a number of systems, the framework does not adequately capture certain aspects of the systems under development by the explanation-based learning group at Illinois. The primary inadequacies arise in the treatment of concept operationality, organization of knowledge into schemata, and learning from observation. This paper outlines six specific problems with the previously proposed framework and presents an alternative generalization method to perform explanation-based learning of new concepts.

We present a model of similarity-based retrieval which attempts to capture three psychological phenomena: (1) people are extremely good at judging similarity and analogy when given items to compare. (2) Superficial remindings are much more frequent than structural remindings. (3) People sometimes experience and use purely structural analogical remindings. Our model, called MAC/FAC (for "many are called but few are chosen") consists of two stages. The first stage (MAC) uses a computationally cheap, non-structural matcher to filter candidates from a pool of memory items. That is, we redundantly encode structured representations as content vectors, whose dot product yields an estimate of how well the corresponding structural representations will match. The second stage (FAC) uses SME to compute a true structural match between the probe and output from the first stage. MAC/FAC has been fully implemented, and we show that it is capable of modeling patterns of access found in psychological ...

A theory of analogical mapping between source and target analogs based upon Interacting structural, semantic, and pragmatic constraints is proposed here. The structural constraint of isomorphism encourages mappings that maximize the consistency of relational corresondences between the elements of the two analogs. The constraint of semantic similarity supports mapping hypotheses to the degree that mapped predicates have similar meanings. The constraint of prog-mafic central/! / favors mappings involving elements the analogist believes to be Important in order to achieve the purpose for which the analogy Is being used. The theory is implemented in a computer program called ACME (Analogical Constraint Mapping Engine), which represents constraints by means of a network of supporting and competing hypotheses regarding what elements to map. A coop-erative algorithm for parallel constraint satisfaction identifies mapping hypotheses that collectively represent the overall mapping that best fits the interacting constraints. ACME has been applied to a wide range of examples that include problem analogies, analogical arguments, explanatory analogies, story analogies, formal analogies, and metaphors. ACME is sensitive to semantic and pragmatic Information if it Is available,.and yet able to compute mappings between formally Isomorphic analogs without any similar or identical elements. The theory Is able to account for empirical findings regarding the impact of consistency and similarity on human processing of analogies.

Selectional constraints are limitations on the applicability of predicates to arguments. For example, the statement “The number two is blue” may be syntactically well formed, but at some level it is anomalous — BLUE is not a predicate that can be applied to numbers. According to the influential theory of (Katz and Fodor, 1964), a predicate associates a set of defining features with each argument, expressed within a restricted semantic vocabulary. Despite the persistence of this theory, however, there is widespread agreement about its empirical shortcomings (McCawley, 1968; Fodor, 1977). As an alternative, some critics of the Katz-Fodor theory (e.g. (Johnson-Laird, 1983)) have abandoned the treatment of selectional constraints as semantic, instead treating them as indistinguishable from inferences made on the basis of factual knowledge. This provides a better match for the empirical phenomena, but it opens up a different problem: if selectional constraints are the same as inferences in general, then accounting for them will require a much more complete understanding of knowledge representation and inference than we have at present. The problem, then, is this: how can a theory of selectional constraints be elaborated without first having either an empirically adequate theory of defining features or a comprehensive theory of inference? In this dissertation, I suggest that an answer to this question lies in the representation of conceptual

In contrast to expectation-based, predictive views of discourse comprehension, a model is developed in which the initial processing is strictly bottom-up. Word meanings are activated, propositions are formed, and inferences and elaborations are produced without regard to the discourse context. However, a network of interrelated items is created in this manner, which can be integrated into a coherent structure through a spreading activation process. Data concerning the time course of word identification in a discourse context are examined. A simulation of arithmetic word-problem under-standing provides a plausible account for some well-known phenomena in this area. Discourse comprehension, from the viewpoint of a computa-tional theory, involves constructing a representation of a dis-course upon which various computations can be performed, the outcomes of which are commonly taken as evidence for com-prehension. Thus, after comprehending a text, one might rea-sonably expect to be able to answer questions about it, recall or summarize it, verify statements about it, paraphrase it, and SO on.

Abstract. Expertise consists of rapid selection and application of compiled experience. Robust reasoning, however, requires adaptation to new contingencies and intelligent modification of past experience. And novel or creative reasoning, by its real nature, necessitates general problem-solving abilities unconstrained by past behavior. This article presents a comprehensive computational model of analogical (case-based) reasoning that transitions smoothly between case replay, case adaptation, and general problem solving, exploiting and modifying past experience when available and resorting to general problem-solving methods when required. Learning occurs by accumulation of new cases, especially in situations that required extensive problem solving, and by tuning the indexing structure of the memory model to retrieve progressively more appropriate cases. The derivational replay mechanism is discussed in some detail, and extensive results of the first full implementation are presented. These results show up to a large performance improvement in a simple transportation domain for structurally similar problems, and smaller improvements when less strict similarity metrics are used for problems that share partial structure in a process-job planning domain and in an extended version of the STRIPS robot domain.

A semantic network or net is a graphic notation for representing knowledge in patterns of interconnected nodes and arcs. Computer implementations of semantic networks were first developed for artificial intelligence and machine translation, but earlier versions have long been used in philosophy, psychology, and linguistics. What is common to all semantic networks is a declarative graphic representation that can be used either to represent knowledge or to support automated systems for reasoning about knowledge. Some versions are highly informal, but other versions are formally defined systems of logic. Following are six of the most common kinds of semantic networks, each of which is discussed in detail in one section of this article. 1. Definitional networks emphasize the subtype or is-a relation between a concept type and a newly defined subtype. The resulting network, also called a generalization or subsumption hierarchy, supports the rule of inheritance for copying properties defined for a supertype to all of its subtypes. Since definitions are true by definition, the information in these networks is often assumed to be necessarily true.

Analogy is often viewed as a partial similarity match between domains. But not all partial similarities qualify as analogy: There must be some selection of which commonalities count. Three experiments tested o particular selection constraint in anological mapping, namely, systemoticity. That is, we tested whether a given predicate is more likely to figure in the interpretation of and prediction from on analogy if the predicate participates in a common system of relations. In Experiment 1, subjects judged two matches to be included in on analogy: an isolated match, and a match embedded in. a larger matching system. Subjects preferred the embedded match. In Experiments 2 and 3, subjects mode analogical predictions about a target domain. Subjects predicted information that followed from a causal system that matched the base domain, rather than information that was equally plausible, but that created an isolated match with the base. Results support Gentner's (1983, 1989) structure. mopping theory in that anological mopping concerns systems and not individual predicates, and that attention to shored systematic structure constrains the selection of information to include in an analogy.

This paper introduces a paradigm of context-dependent grammar (CDG) and an acquisition system that, through interactive teaching sessions, accumulates the CDG rules. The resulting context-sensitive rules are used by a stack-based, shift~reduce parser to compute unambiguous syntactic structures of sentences. The acquisition system and parser have been applied to the phrase structure and case analyses of 345 sentences, mainly from newswire stories, with 99 % accuracy. Extrapolation from our current grammar predicts that about 25 thousand CDG rule examples will be sufficient to train the system in phrase structure analysis of most news stories. Overall, this research concludes that CDG is a computationally and conceptually tractable approach for the construction of sentence grammar for large subsets of natural language text. 1.

This work analyzes the central role of interpretation in non-routine design. Based on this analysis, a theory of computer support for interpretation in cooperative design is constructed. The theory is grounded in studies of design and interpretation. It is illustrated by mechanisms provided by a software substrate for computer-based design environments, applied to a sample task of lunar habitat design. Computer support of