Abstract not found

Transfer learning concerns applying knowledge learned in one task (the source) to improve learning another related task (the target). In this paper, we use structure mapping, a psychological and computational theory about analogy making, to find mappings between the source and target tasks and thus construct the transfer functional automatically. Our structure mapping algorithm is a specialized and optimized version of the structure mapping engine and uses heuristic search to find the best maximal mapping. The algorithm takes as input the source and target task specifications represented as qualitative dynamic Bayes networks, which do not need probability information. We apply this method to the Keepaway task from RoboCup simulated soccer and compare the result from automated transfer to that from handcoded transfer.

Computational models of analogical problem solving have traditionally described source and target domains in terms of their causal structure. But psychological research shows that visual reasoning plays a part for many kinds of analogies. This paper describes a model that transfers a solution from a source analog to a new target problem using only visual knowledge represented symbolically. The knowledge representation is based on a language of primitive visual elements and transformations. We found that visual knowledge is sufficient for transfer, but that causal knowledge is needed to determine if the transferred solution is appropriate. 1

This paper proposes a new paradigm and a computational framework for revealing equivalencies (analogies) between sub-structures of distinct composite systems that are initially represented by unstructured data sets. For this purpose, we introduce and investigate a variant of traditional data clustering, termed coupled clustering, which outputs a configuration of corresponding subsets of two such representative sets. We apply our method to synthetic as well as textual data. Its achievements in detecting topical correspondences between textual corpora are evaluated through comparison to performance of human experts.

questions of Cognitive Science. Recently Marcus et al.

We review the work of Evans on graphical proportional analogies, identifying the object mappings that underlie many such comparisons. The limitations of Evans ANALOGY model are investigated. We then establish the role of attributes (colour, shape, pattern etc) in such analogies and identify two distinct mapping algorithms that are required by different classes of geometric analogy problems. We identify the conditions under which the alternate algorithms are required to produce a "best" answer. Finally, we describe a computational model (LUDI) that automatically generates the result for a large number of geometric analogies.

Abstract. This paper defines and analyses a computational model of similarity which detects analogies between objects based on conceptual descriptions of them, constructed from classification, generalization relations and attributes. Analogies are detected(elaborated) by functions which measure conceptual distances between objects with respect to these semantic modelling abstractions. The model is domain independent and operational upon objects described in non uniform ways. It doesn’t require any special forms of knowledge for identifying analogies and distinguishes the importance of distinct object elements. Also, it has a polynomial complexity. Due to these characteristics, it may be used in complex tasks involving intra or inter-domain analogical reasoning. So far the similarity model has been applied in the domain of software engineering. First, to support the specification of software requirements by analogical reuse and second, to enable the integration of requirements specifications, generated by the multiple agents involved in information system development. Details of these applications can be found in sited references. Also, we have conducted an empirical evaluation of: (i) the consistency of the estimates generated by the model against human intuition about similarity and (ii) its recall performance in tasks of analogi-cal retrieval, the results of which are presented in this paper. 1.

This thesis is concerned with the development of an under-lying model of memory to support selective case retrieval for case-based reasoning. The major requirements are that retrieval should be highly flexible yet efficient. The traditional approach of "indexing" is rejected as being too restrictive while more flexible approaches in analogical reasoning are generally too computationally expensive. Several important organisational principles are developed in the memory model. A network representation is advocated with a number of required extensions; such as multi-granular representation, context-based segregation and a statistically-based grading of paths. The organisation of memory offers the potential for the serial performance of a number of retrieval tasks that have previously only been addressed by assuming a massively parallel implementation. The retrieval mechanism developed is a novel activation passing technique that creates a gradation of stored cases during retrieval. Empiri...

Models that rely exclusively on static representations cannot account fully for the flexibility of human analogy-making. More

Measuring the similarity between semantic relations that hold among entities is an important and necessary step in various Web related tasks such as relation extraction, information retrieval and analogy detection. For example, consider the case in which a person knows a pair of entities (e.g. Google, YouTube), between which a particular relation holds (e.g. acquisition). The person is interested in retrieving other such pairs with similar relations (e.g. Microsoft, Powerset). Existing keyword-based search engines cannot be applied directly in this case because, in keyword-based search, the goal is to retrieve documents that are relevant to the words used in a query – not necessarily to the relations implied by a pair of words. We propose a relational similarity measure, using a Web search engine, to compute the similarity between semantic relations implied by two pairs of words. Our method has three components: representing