Physical Bongard Problems
نویسندگان
چکیده
In this paper, we introduce Physical Bongard Problems (PBPs) as a novel and potentially rich approach to study the impact the constraints of a physical world have on mechanisms of concept learning and scene categorization. Each PBP consists of a set of 2D physical scenes which are positive or negative examples of a concept that must be identified. We discuss the properties that make PBPs challenging, analyze computational and representational requirements for a computational solver, and describe a first implementation of such a system. It can solve a subset of non-trivial PBPs using a version space approach for achieving its scene categorizations. The key element is a physics engine that is used both for the construction of information-rich physical features and for the prediction of how a given situation might evolve.
منابع مشابه
A glimpse at the metaphysics of Bongard problems
Bongard problems present an outstanding challenge to artificial intelligence. They consist of visual pattern understanding problems on which the task of the pattern perceiver is to find an abstract aspect of distinction between two classes of figures. This paper examines the philosophical question of whether objects in Bongard problems can be ascribed an a priori, metaphysical, existence — the ...
متن کاملThe effect of overt language use on category induction
Successfully solving a problem should help people solve similar problems, but such generalization is often surprisingly limited. We investigated generalization performance when people explicitly verbalized solutions to open-ended categoryinduction ”Bongard problems”, compared to tacitly indicating that they had found a solution. In a Bongard problem people are presented with an array of items f...
متن کاملSimilarity-based Ordering of Instances for Efficient Concept Learning
Theories in concept learning predict that interleaving instances of different concepts is especially beneficial if the concepts are highly similar to each other, whereas blocking instances belonging to the same concept provides an advantage for learning low-similarity concept structures. This suggests that the performance in concept learning tasks can be improved by grouping the instances of gi...
متن کاملGrouping by Similarity Helps Concept Learning
In inductive learning, the order in which concept instances are presented plays an important role in learning performance. Theories predict that interleaving instances of different concepts is especially beneficial if the concepts are highly similar to each other, whereas blocking instances belonging to the same concept provides an advantage for learning lowsimilarity concept structures. This l...
متن کاملSome topics of current interest in clustering : Russian approaches 1960 - 1985
Early developments in data analysis in Russia, and in the Soviet Union in general have been well separated by the rather tight iron curtain through all of the covered period. However, they generally followed the international developments, because some monographs were translated into Russian, best journals reached a few libraries with a lag of one-two years, and a few Soviet scientists did atte...
متن کامل