Bayesian analogy with relational transformations.
نویسندگان
چکیده
منابع مشابه
Bayesian analogy with relational transformations.
How can humans acquire relational representations that enable analogical inference and other forms of high-level reasoning? Using comparative relations as a model domain, we explore the possibility that bottom-up learning mechanisms applied to objects coded as feature vectors can yield representations of relations sufficient to solve analogy problems. We introduce Bayesian analogy with relation...
متن کاملAnalogy and Relational Reasoning
Analogy is an inductive mechanism based on structured comparisons of mental representations. It is an important special case of role-based relational reasoning, in which inferences are generated on the basis of patterns of relational roles. Analogical reasoning is a complex process involving retrieval of structured knowledge from long-term memory, representing and manipulating role-filler bindi...
متن کاملRelational Language Facilitates Analogy in Children
One important function of language is to name relations. Preschool children performed a simple mapping task with and without hearing spatial prepositions calling attention to key relations. Children at 44 months were successful only if they were in the language condition. By 49 months, children were competent on the task regardless of condition, although there were still benefits of language. T...
متن کاملGraph Transformations in Relational Databases
We present a novel approach to implement a graph transformation engine based on standard relational database management systems (RDBMSs). The essence of the approach is to store not only the instance graphs in relational database tables but also keep track explicitly of all the matchings of graph transformation rules in database views. Furthermore, the model manipulation prescribed by the appli...
متن کاملEncoding Spatial Domains with Relational Bayesian Networks
This paper investigates an encoding of a probabilistic TBox using relational Bayesian networks that are specified through a probabilistic description logic. The probabilistic description logic extends the popular ALC language; on top of this language we add a few operations that are needed to represent the cardinal direction calculus. Using such resources we model roads containing lanes, and ve...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Psychological Review
سال: 2012
ISSN: 1939-1471,0033-295X
DOI: 10.1037/a0028719