This article describes an integrated theory of analogical access and mapping, instantiated in a

is provided in screen-viewable form for personal use only by members

Distributed representations are attractive for a number of reasons. They offer the possibility of representing concepts in a continuous space, they degrade gracefully with noise, and they can be processed in a parallel network of simple processing elements. However, the problem of representing nested structure in distributed representations has been for some time a prominent concern of both proponents and critics of connectionism [Fodor and Pylyshyn 1988; Smolensky 1990; Hinton 1990]. The lack of connectionist representations for complex structure has held back progress in tackling higher-level cognitive tasks such as language understanding and reasoning. In this thesis I review connectionist representations and propose a method for the distributed representation of nested structure, which I call "Holographic Reduced Representations " (HRRs). HRRs provide an implementation of Hinton's [1990] "reduced descriptions". HRRs use circular convolution to associate atomic items, which are rep...

Abstract not found

The use of analogy in human thinking is examined from the perspective of a multiconstraint theory, which postu-lates 3 basic types of constraints: similarity, structure, and purpose. The operation of these constraints is appar-ent in laboratory experiments on analogy and in natural-istic settings, including politics, psychotherapy, and sci-entific research. The multiconstraint theory has been im-plemented in detailed computational simulations of the analogical human mind. ~ ~ any parents know that young children take comfort in getting a kiss on an injury to "make it better. " Little Aaron, aged 24 months, would routinely come to his mother saying things like, "I bump my head. Kiss it. " But one morning, for the first time ever, the tables turned. While his mother was dressing

This paper begins with a brief review of SME and MAC/FAC, our simulations of matching and retrieval. Next I lay out several arguments for exploring analogy in the large, including why it is now very feasible and what we can learn by such explorations. A new constraint on cognitive simulations, the Integration Constraint, is proposed: A cognitive simulation of some aspect of analogical processing should be usable as a component in larger-scale cognitive simulations. I believe that the implications of this new constraint for cognitive simulation of analogy are far-reaching. After that, two explorations of larger-scale phenomena are described. First, I describe a theoretical framework in which we model common sense reasoning as an interplay of analogical and first-principles reasoning. Second, I describe how SME and MAC/FAC have been used in a case-based coach that is accessible to engineering thermodynamics students worldwide via electronic mail. These examples show that exploring analogy in the large can provide new insights and new challenges to our simulations. Finally, the broader implications of this approach are discussed.

The retrieval of a suitable case is of crucial importance to the success of case-based reasoning. A good criterion for judging "case suitability" is how complex a case will be to adapt. However, it has proven difficult to directly calculate this measure of case "adaptability" without incurring the full cost of adaptation. This has led most researchers to exploit semantic similarity as a more tractable (albeit less accurate) answer to the question of case suitability. This paper

Recent constraint-satisfaction models of explanation, analogy, and decision making claim that these processes are influenced by bidirectional constraints that promote coherence. College students were asked to reach a verdict in a complex legal case involving multiple conflicting arguments, including alternative analogies to the target case. Participants rated agreement with the individual arguments both in isolation before seeing the case, and again after reaching a verdict. Assessments of the individual arguments (including the competing analogies) shifted so as to cohere with their emerging verdict. Information about the character of the defendant in the initial case triggered a cascade of "spreading coherence", influencing decisions made about a subsequent case involving very different legal issues. Participants ' memory for their initial positions also shifted so as to cohere with their final positions. The coherence shifts were simulated by a constraint satisfaction model. The results demonstrate that an alogical process of constraint satisfaction can transform highly ambiguous inputs into coherent decisions. Bidirectional Reasoning 3 One of the most deep-rooted assumptions about human reasoning is that the flow of

This paper presents several challenges to the models of analogy-making, namely the need for building integrated models, the need for using dynamic and emergent representations, the need for using dynamic and emergent computation, and the need to integrate analogy-making with other cognitive processes. Some experimental data are reviewed which substantiate these needs and the main ideas how the AMBR model of analogy-making could meet these challenges are presented. 1. From the Anatomy towards the Physiology of AnalogyMaking: The Need for Integrated and Dynamic Models For a long time now the research on analogy has concentrated on the anatomy of analogymaking, i.e. on decomposing it into pieces (representation building, retrieval, mapping, transfer, evaluation, learning) and trying to understand how each individual piece works. A number of successful models of various subprocesses (mainly of mapping and retrieval) have been built which account for most of the psy...

Hofstadter and his colleagues have criticized current accounts of analogy, claiming that such accounts do not accurately capture interactions between processes of representation construction and processes of mapping. They suggest instead that analogy should be viewed as a form of high level perception that encompasses both representation building and mapping as indivisible operations within a single model. They argue specifically against SME, our model of analogical matching, on the grounds that it is modular, and offer instead programs such as Mitchell and Hofstadter's Copycat as examples of the high level perception approach. In this paper we argue against this position on two grounds. First, we demonstrate that most of their specific arguments invo lving SME and Copycat are incorrect. Second, we argue that the claim that analogy is high-level perception, while in some ways an attractive metaphor, is too vague to be useful as a technical proposal. We focus on five issues: (1) how perception relates to analogy, (2) how flexibility arises in analogical processing, (3) whether analogy is a domain-general process, (4) how micro-worlds should be used in the study of analogy, and (5) how best to assess the psychological plausibility of a model of analogy. We illustrate our discussion with examples taken from computer models embodying both views.