Hofstadter, D. R., & Mitchell, M. (1994). An overview of the Copycat project. In K. J. Holyoak & J. A. Barnden (Eds.), Advances in Connectionist and Neural Computation Theory: Vol. 2. Analogical Connections (pp. 31-112). Hillsdale, NJ: Lawrence Erlbaum Associates.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....addition, we show that path mapping models can account for lower level behavior in the execution of analogy not addressed by other theories. Current Theories of Analogical Mapping Numerous researchers have proposed theories that describe how analogical mapping takes place (Gentner, 1983, 1989; Hofstadter Mitchell, 1994; Holyoak Thagard, 1989; Hummel Holyoak, 1997; Keane, Ledgeway, Duff, 1994; Kokinov, 1998) These theories have made great strides in accounting for what we know of the mapping process. For instance, the theories have accounted for similarity effects between corresponding objects (Ross, ....

Hofstadter, D. R., & Mitchell, M. (1994). An overview of the Copycat project. In K. J. Holyoak & J. A. Barnden (Eds.), Advances in Connectionist and Neural Computation Theory: Vol. 2. Analogical Connections (pp. 31-112). Hillsdale, NJ: Lawrence Erlbaum Associates.

....high level concepts and low level perceptual processes: high level concepts influence low level perceptual processing, while what is perceived at a low level affects the activation of high level concepts as a representation of the situation is constructed. 1 The Copycat project, designed by Hofstadter and Mitchell (1992; Mitchell, 1990, 1993; Mitchell 1 The conceptual level is the level at which concepts begin to play a role; a concept is anything from object recognition (e.g. recognizing an apple) to the ability to grasp complex relations and situations (e.g. that Bill Clinton is in the Democratic ....

Hofstadter, D. R. & Mitchell, M. (1992). An overview of the Copycat project. In Holyoak, K.J. & Barnden, J.

....checking the justifications. A symbol mapping is possible in Prodigy Analogy by type preserving instantiations. This amounts to a simple level of reformulation. 4. 2 A Neural Network Approach Several computational analogy systems utilize neural nets and reinforcement learning, among them COPYCAT [59] and ACME. Holyoak and Thagard [63] designed a system called ACME (Analogical Constraint Mapping Engine) and a system ARCS (Analog Retrieval by Constraint Satisfaction) 135] that both use a connectionist architecture. These systems are based on results from psychological research as well as ....

D.R. Hofstadter and M. Mitchell. An overview of the copycat project. Tech Report CRCC-52-1991, Indiana University Bloomington, Indiana, 1991.

....of the continuum. Finally its functionality depends on macrosemantics and therefore it has been positioned at the symbolic end of the functionality dimension. 1.4. 4 Copycat Another system which lies in the Gap is Copycat, a program designed to solve idealized analogy problems [Hofstadter, 1984, Hofstadter and Mitchell, 1991] These analogies are stated in terms of letter strings: given that letter string1 changes into letter string2, what does letter string3 change into A typical problem might be: if abc abd then ijk When presented with a particular analogy problem, Copycat gradually builds an internal ....

Hofstadter, D. R. and Mitchell, M. (1991). An overview of the Copycat project. To appear in Holyoak and Barnden, editors, Connectionist Approaches to Analogy, Metaphor and Case-Based Reasoning. Ablex.

....here works in a domain of alphabetical letter strings. This domain is simple enough that the problems of low level perception are avoided, but complex enough that the main issues in high level perception arise and can be studied. The model, the Copycat program (Hofstadter 1984; Mitchell 1990; Hofstadter and Mitchell 1992), is capable of building up its own representations of situations in this domain, and does so in a flexible, contextdependent manner. Along the way, many of the central problems of high level perception are dealt with, using mechanisms that have a much broader range of application than just this ....

....of many possible paths toward a representation; the radical restructuring of perceptions, when necessary. The description of Copycat given here will necessarily be brief and oversimplified, but further details are available elsewhere (Hofstadter 1984; Mitchell and Hofstadter 1990; Mitchell 1990; Hofstadter and Mitchell 1992). The Copycat domain The task of the Copycat program is to make analogies between strings of letters. For instance, it is clear to most people that abc and iijjkkll share common structure at some level. The goal of the program is to capture this by building, for each string, a representation that ....

[Article contains additional citation context not shown here]

Hofstadter, D. R., and Mitchell, M. (1992). An overview of the Copycat project. In K. J.

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