, Machine Learning: An Artificial Intelligence Approach, vol. II. Tioga Press, Palo Alto, California, 1982.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....which case the refactoring described in the next section is invoked. These heuristics detect similarities based on a small set of structural attributes. More powerful similarity detection is possible, as discussed in the artificial intelligence machine learning literature on analogy based systems [28, 39, 51, 64]. Analogy based systems have very limited power unless their analysis is based on a well defined domain model. Such approaches are of dubious value in many applications of refactoring, where the design of the application is not well understood and is evolving. 6.3 Adding Function Signatures to ....

M. H. Burstein. Concept formation by incremental analogical reasoning and debugging. Machine Learning: An Artificial Intelligence Approach (R.S. Michalski, J. G. Carbonell and T. M. Mitchell, eds), 2:351 370, 1986.

....SBL are often applied here. Furthermore, since similarities might be found at a different level from the purely superficial one of entities observable characteristics, the entities are often analyzed using deductive, or explanation based, mechanisms as well. Examples of work in analogy include [Burstein 86; Carbonell 83a; Carbonell 83b; Kedar Cabelli 85; Russell 86] Exemplar based learning is another mechanism that combines inductive and deductive techniques. In exemplar based learning a concept is represented by a stereotypical example. Deduction, or explanation derivation, is used to determine ....

Burstein, M. H. Concept Formation by Incremental Analogical Reasoning and Debugging. Machine Learning: An Artificial Intelligence Approach, Volume II. Morgan Kaufmann, Los Altos, California, 1986.

....which case the refactoring described in the next section is invoked. These heuristics detect similarities based on a small set of structural attributes. More powerful similarity detection is possible, as discussed in the artificial intelligence machine learning literature on analogy based systems [28, 39, 51, 64]. Analogy based systems have very limited power unless their analysis is based on a well defined domain model. Such approaches are of 88 dubious value in many applications of refactoring, where the design of the application is not well understood and is evolving. 6.3 Adding Function Signatures ....

M. H. Burstein. Concept formation by incremental analogical reasoning and debugging. Machine Learning: An Artificial Intelligence Approach (R.S. Michalski, J. G. Carbonell and T. M. Mitchell, eds), 2:351--370, 1986.

....episodes is an important issue for several reasons. First, it should place further constraints on theories of analogy. Second, it also has practical implications for the use of analogies in education. Students are often given successive analogy problems in the course of learning a topic (see e.g. Burstein, 1986; Mayer Bromage, 1980) So, we need to understand what students derive from each of these episodes, if analogies are to be used effectively in educational contexts. Table 1 About Here The Problem of Transfer Between Analogies: Previous Research Two main accounts of analogical transfer exist in ....

Burstein, M.H. (1986). Concept formation by incremental analogical reasoning and debugging. In R.S. Michalski, J.G. Carbonell & J.M. Mitchell (Eds.), Machine learning II: An artificial intelligence approach . Los Altos, Calif.: Kaufmann.

....effects using the two versions of the attribute mapping problem shown in Table 1. An important property of these attribute mapping problems is that each list has two individuals (e.g. Bill and Tom) with two attributes (termed 1 Different forms of incrementality have been proposed in analogy. Burstein (1986) proposed that multiple base domains could be combined incrementally over time when learning by analogy, but this model does not apply to complex analogies. Falkenhainer (1987) proposed a mechanism for the incremental revision of analogical inferences after they had been tested by a simulation ....

Burstein, M.H. (1986). Concept formation by incremental analogical reasoning and debugging. In R.S.

....plans then the performance task might be to modify the retrieved old plan to suit the current problem. These types of performance tasks, when using exemplar like schemes, require substantial analogical reasoning following retrieval which we do not consider in this document (see for example [3], 5] 4] 2.2 Classical representations To contrast the use of classical and exemplar based concept models, consider what such models might look like for the categories bird and elephant given the following training data : attributes class size legs colour habitat big talons brown ....

M. Burstein. Concept formation by incremental analogical reasoning and debugging. In J. G. Carbonell, R. S. Michalski, and T. M. Mitchell, editors, Machine Learning, vol. 2, Tioga, Palo Alto, Ca, 1986.

....features of the source case to be tweaked [74] in a way that is similar to the indexing transformation strategies discussed at the end of section 5.2.2. Another common approach is simply to replace incompatible components of a source case with an equivalent component from a different source case [20, 61, 73, 33, 110]. This latter approach effectively merges multiple source cases to create a composite source case that more completely matches and satisfies the requirements of the target case 7 . These two approaches to adaptation, it is proposed, can be unified in a single model recasting adaptation as ....

Mark H Burstein. Concept Formation by Incremental Analogical Reasoning and Debugging. In R S Michalski, J G Carbonell, and T M Mitchell, editors, Machine Learning: an A.I. approach, pages pp351--367. Morgan Kaufmann Publishers, 1986. vol II.

....model of analogy making is the Structure Mapping Engine (SME) Falkenhainer, Forbus, and Gentner 1990) based upon the structure mapping theory of Dedre Gentner (1983) We will examine this model within the context of our earlier remarks. Other models of analogy making, such as those of Burstein (1986), Carbonell (1986) Holyoak Thagard (1989) Kedar Cabelli (1988) and Winston (1982) while differing in many respects from the above work, all share the property that the problem of representation building is bypassed. Let us consider one of the standard examples from this research, in which ....

....then have ignored the problem of representation building. The work of Kedar Cabelli (1988) takes a limited step in this direction by employing a notion of purpose to direct the selection of relevant information, but still starts with all representations pre built. Other researchers, such as Burstein (1986), Carbonell (1986) and Winston (1982) all have models that differ in significant respects from the work outlined above, but none of these addresses the question of perception. The ACME program of Holyoak and Thagard (1989) uses a kind of connectionist network to satisfy a set of soft ....

Burstein, M. (1986). Concept formation by incremental analogical reasoning and debugging. In R. S. Michalski, J. G. Carbonell, and T. M. Mitchell (eds.), Machine learning: An artificial intelligence approach, Vol. 2 (Los Altos, CA: Morgan Kaufmann).

....extra run through the target, looking for plausible matches. It would be interesting to see how the program handles a more complex analogy such as El Salvador is analogous to Vietnam , with a full base and target representation. Insert Figure 2 about here Some theorists (Carroll and Mack, 1985; Burstein, 1986; Holland, Holyoak, Nisbett Thagard, 1986) have claimed that, without the use of goals, the structure mapping theory would be hopelessly inefficient and by itself insufficient to guide the processing of analogies. Gentner (in press) believes that SME has proved them wrong, because it generates ....

Burstein, M.H. (1986). Concept formation by incremental analogical reasoning and debugging.

.... Engine(SME) 17] the Constraint Satisfaction Theory(CST) implemented by ACME [28] and ARCS[65] and the Constrained Semantic Transference(CST) 29] 2) models of analogical understanding which detect analogies to explain unfamiliar domains in terms of familiar ones, e.g. MACKBETH[72] and CARL[7]) 3) models of analogical problem solving, which detect analogies to solve specific problems and involve analogs from different domains(e.g. ANA[41] explicit planning[45] MEDIATOR[37] ARCHES[5] purpose directed analogy[30] transformational and derivational analogy[8, 9, 43] NLANG[23] ....

Burstein M., Concept Formation By Incremental Analogical Reasoning and Debugging, Machine Learning: An Artificial Intelligence Approach, Vol. II, Morgan Kaufmann Publishers Inc., Los Altos, California, 1986

No context found.

, Machine Learning: An Artificial Intelligence Approach, vol. II. Tioga Press, Palo Alto, California, 1982.

No context found.

M. H. Burstein. Concept formation by incremental analogical reasoning and debugging. In R. S. Michalski, J. G. Carbonell, and T. M. Mitchell, editors, Machine Learning: An Artificial Intelligence Approach, (Vol. 2). Morgan Kaufmann, San Mateo, CA, 1986.

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