Evans, T. (1968) A Program for the Solution of a Class of Geometric-Analogy Intelligence-Test Questions, Semantic Information Processing, 1968, MIT Press.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....least to exhibit quite startling learning behaviours. But following Minsky and Papert s exhaustive evaluation of the theoretical properties of the perceptron [1] the subsymbolic paradigm sank back while the symbolic paradigm came to the fore with systems such as Evans analogy solving program [2] and later Winston s work on learning and vision [3, 4] All through the 70s the symbolic paradigm was in a leading position but towards the end of the decade the subsymbolic paradigm began to show a marked increase in activity and in the early years of the next decade (the 80s) we saw the ....

Evans, T. (1968). A program for the solution of a class of geometric-analogy intelligence-test questions. In M. Minsky (Ed.), Semantic Information Processing. Cambridge, Mass.: MIT Press.

.... such that t 1 = t 2 . The subsumes relation induces a partial order on the set of terms. The least upper bound under subsumption is called the least general generalization (lgg) We also use the notion of position as defined in [6] Positions are sequences of positive integers (e.g. [2,3,2]) ffl denotes the empty position, and Delta the concatenation operation on positions. With t a term or atom the sub term of t at position u, t=u is defined as follows: If t is a term, then t=ffl = t. if t = f(t 1 ; t n ) then t= i Delta u) t i =u. In instance based learning ....

.... unknown output N out such that p(N in ; N out ) Suppose e.g. we have an example p(in(circle; square) in(square; circle) and have to find the output of in(circle; triangle) see figure 1) The program could then answer in(triangle; circle) This is also an example of learning by analogy (cf. [3]) 4 Instance based function learning In the attribute value setting, the process of predicting a class for an example with the k nearest neighbours method can be divided in three important steps. First, the example input is compared using a distance with all the training example inputs and the ....

[Article contains additional citation context not shown here]

Thomas G. Evans. A program for the solution of a class of geometric-analogy intelligence-test questions. In Marvin L. Minsky, editor, Semantic Information Processing, pages 271--353. MIT Press, Cambridge, Massachusetts, 1968.

....doing line detection, which is essential in machine vision, but not critical in diagrammatic reasoning. Using line drawings also makes diagram input simple: diagrams can be built using an offthe shelf drawing program (Hendrich, 1999) Line drawings have been successful in several systems (e.g. Evans, 1968; Gross, 1996; Sutherland, 1963) and work well with existing spatial reasoning models. The output of GeoRep is a description of the figure expressed in a domain dependent high level place vocabulary. Like previous approaches to spatial representation, the representation produced by GeoRep ....

Evans, T. G. (1968). A program for the solution of a class of geometric-analogy intelligence-test questions. In M. Minsky (Ed.), Semantic Information Processing (pp. 271353) . Cambridge, MA: MIT Press.

....contextualization e ect, and the principles underlying our algorithm are clearly and formally explicated. We would like to make some remarks now comparing our algorithm to the other existing approaches to solving proportional analogy problems. In the early days of arti cial intelligence research, Evans (1968) implemented a system for solving proportional analogy problems in the geometric gures domain. However, in Evans system, the representations of the gures (terms of the analogy relation) were determined rst, and then the mappings were computed. Though Evans explicitly discusses the mutual ....

Evans, T. (1968). A program for the solution of a class of geometric-analogy intelligence-test questions. In Minsky, M., editor, Semantic Information Processing, pages 271-353, Cambridge, Mass. MIT Press.

....Models Recall that the non traditional models do not subscribe to the traditional assumptions. Like the traditional models, the non traditional models come in GOFAI and connectionist versions. 6.2. 1 Evans ANALOGY program The first AI program to address head on the issues of analogy making was Evans ANALOGY program (1968). ANALOGY was designed to answer proportional geometric analogy problems (see Figure 6 5) that were, at one time, common on American I.Q. tests. The idea of the ANALOGY task is to answer the question if the picture A changes into picture B, then what does picture C change into The question is ....

Evans, T. G. (1968). A program for the solution of a class of geometric analogy intelligence test questions. In Semantic Information Processing (Minsky, M., ed.). MIT Press, Cambridge, Mass., pp. 271-253.

....properties along a chain. The next step of this modelization would be to pair higher order structures. CONCLUSION Different computational models have been developed to model analogy solving and are based on different representational structures. Among them, the ANALOGY system proposed by Evans (Evans, 1968) uses rules, the SME system proposed by Falkenhainer to illustrate Gentner s theory for analogy (Falkenhainer et al. 1989; Gentner, 1983) uses propositional structures, the ARCS system developed by Thagard and Holyoak to simultaneously satisfy the structural, semantic and pragmatic constraints ....

Evans, T. G. (1968). A program for the solution of a class of geometric analogy intelligence-test questions. In Semantic Information Processing, chapter 5, pages 271--353. The MIT Press.

....of knowledge representation. The task is to answer a typical IQ test by giving an element called D such that it completes a four term analogy with three other given elements A; B and C: i nd D such that it is to C what B is to Aj. This kind of analogy solving has already been studied by Evans [Eva68], but in our work the solution has to be build from scratch since no set of possible solutions is given to choice. We call this kind of IQ test like problems, non supervised. This four term analogy solving is usually decomposed into four steps [Eva68] ffl Find the possible relations RAB between ....

....solving has already been studied by Evans [Eva68] but in our work the solution has to be build from scratch since no set of possible solutions is given to choice. We call this kind of IQ test like problems, non supervised. This four term analogy solving is usually decomposed into four steps [Eva68]. ffl Find the possible relations RAB between A and B. ffl Find the possible relations RAC between A and C. ffl Apply RAB to C only on a domain determined with RAC . ffl Verify the symmetry by applying RAC to B. 6.1 Diagrammatic Representation of the problem Usually, IQ tests are given in ....

[Article contains additional citation context not shown here]

Thomas G. Evans. A program for the solution of a class of geometric analogy intelligence-test questions. In Semantic Information Processing, chapter 5, pages 271353. The MIT Press, 1968.

....assumption cannot be made in modeling creative metaphor. O Hara (1992; forthcoming) has been developing a model of re description in the context of geometric proportional analogies inspired by Indurkhya (1989; 1991; 1992) The solution of geometric proportional analogies were also modeled by Evans (1968). Evans did not attempt to integrate the mapping and description building processes as we do here. The description module assumption appears in a slightly different guise in the selection of indices for case retrieval. We (O Hara Indurkhya 1994) have argued that a re description capability was ....

Evans, T. G. 1968. A program for the solution of a class of geometric-analogy intelligence-test questions.

....we apply Van der Helm and Leeuwenberg s algorithm to find the minimum cost path in this modified graph. We would like to make some remarks now comparing our algorithm to the other existing approaches to solving proportional analogy problems. In the early days of artificial intelligence research, Evans (1968) implemented a system for solving proportional analogy problems in the geometric figures domain. However, in Evans system, the representations of the figures (terms of the analogy relation) were determined first, and then the mappings were computed. Thus, Evans system could not model the mutual ....

Evans, T.G. (1968). A Program for the Solution of a Class of Geometric-Analogy Intelligence-Test Questions. In M. Minsky (ed.), Semantic Information Processing.

....application domain [25] The task is to answer a typical IQ test by giving an element called D such that it completes a four term analogy with three other given elements A; B and C: find D such that it is to C what B is to A . This kind of analogy solving has already been studied by Evans [6], but in our work the solution has to be build from scratch since no set of possible solutions is given to choice. We call this kind of IQ test like problems, non supervised. This four term analogy solving is usually decomposed into four steps [6] ffl Find the possible relations RAB between A ....

....analogy solving has already been studied by Evans [6] but in our work the solution has to be build from scratch since no set of possible solutions is given to choice. We call this kind of IQ test like problems, non supervised. This four term analogy solving is usually decomposed into four steps [6]: ffl Find the possible relations RAB between A and B. ffl Find the possible relations RAC between A and C. ffl Apply RAB to C only on a domain determined with RAC . ffl Verify the symmetry by applying RAC to B. To solve a four term analogy, we propose to represent each figure by a simplex ....

[Article contains additional citation context not shown here]

Thomas G. Evans, `A program for the solution of a class of geometric analogy intelligence-test questions', in Semantic Information Processing, chapter 5, 271--353, The MIT Press, (1968).

.... A is to B as C is to using one of the figures D , E , F or G in the position marked with . For this example, the correct answer is clearly E . Computer based methods for solving this kind of problem have existed for some time (e.g. Evans s well known heuristic algorithm [11]) In recent work [16, 15] MLE principles have been applied to good effect. The proposal here is that, within the general framework of MLE, this kind of problem may be understood in terms of ICMAUS. Please insert Figure 26 about ....

....of alpha numeric symbols like the patterns in other examples in this report. For example, item A in Figure 26 may be described as small circle inside large triangle . How this kind of translation may be done is not part of the present proposals (one such translation mechanism is described in [11]) As has been pointed out previously [15] successful solution of this kind of problem depends on consistency in the way the translation is done. For this example, it would be unhelpful if item A in Figure 26 were described as large triangle outside small circle while item C were described ....

Evans, T. G. (1968) A Program for the Solution of a Class of Geometric-Analogy Intelligence-Test Questions. In M. Minsky (ed.), Semantic Information Processing, Cambridge Mass.: MIT Press, pp. 271-353.

....is necessarily wrong: it is simply not tackling what are, in our opinion, the really difficult issues in analogy making. Such criticisms apply equally to most other work in the modeling of analogy. It is interesting to note that one of the earliest computational models of analogy, Evans ANALOGY (Evans 1968), attempted to build its own representations, even if it did so in a fairly rigid manner. Curiously, however, almost all major analogy making programs since then have ignored the problem of representation building. The work of Kedar Cabelli (1988) takes a limited step in this direction by ....

Evans, T. G. (1968). A program for the solution of a class of geometric-analogy intelligence-test questions. In M. Minsky (ed.), Semantic information processing (Cambridge, MA: MIT Press).

....of knowledge representation. The task is to answer a typical IQ test by giving an element called D such that it completes a fourterm analogy with three other given elements A; B and C: find D such that it is to C what B is to A . This kind of analogy solving has already been studied by Evans [Eva68], but in our work the solution has to be build from scratch since no set of possible solutions is given to choice. We call this kind of problems, non supervised IQ tests. This four term analogy solving is usually decomposed into four steps [Eva68] 4 A running computational model called IGLOO is ....

....analogy solving has already been studied by Evans [Eva68] but in our work the solution has to be build from scratch since no set of possible solutions is given to choice. We call this kind of problems, non supervised IQ tests. This four term analogy solving is usually decomposed into four steps [Eva68]. 4 A running computational model called IGLOO is being implemented in the ML programming language. See http: www.lri.fr erika HTML igloo.html for future developments of the IGLOO system. ffl Find the possible relations RAB between A and B. ffl Find the possible relations RAC between A ....

Thomas G. Evans. A program for the solution of a class of geometric analogy intelligence-test questions. In Semantic Information Processing, chapter 5, pages 271-- 353. The MIT Press, 1968.

No context found.

Evans, T. (1968) A Program for the Solution of a Class of Geometric-Analogy Intelligence-Test Questions, Semantic Information Processing, 1968, MIT Press.

No context found.

T.G. Evans. A program for the solution of a class of geometric-analogy intelligence-test questions. In Marvin Minsky, editor, Semantic Information Processing, pages 271--353. MIT Press, Cambridge, MA, 1968.

No context found.

G. Evans. A Program for the Solution of a Class of Geometric-Analogy Intelligence-Test Questions. In Minsky, M., ed. Semantic InformationProcessing, pages 271--353, Cambridge, Massachusetts, 1968. MIT Press

No context found.

Evans, T. G. 1968, "A program for the solution of a class of geometric-analogy intelligence test questions", In "Semantic Information Processing", (Ed.) M. Minsky, MIT Press.

No context found.

Evans, T. G. (1968). A program for the solution of a class of geometric analogy intelligence test questions. In Semantic Information Processing (Minsky, M., ed.).

No context found.

) Evans, T. G., "A Program for the Solution of a Class of Geometric-Analogy Intelligence-Test Questions," in M. Minsky (ed.), Semantic Information Processing, Cambridge Mass.: MIT Press, pp. 271-353, 1968.

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