Skip to Main content Skip to Navigation
Conference papers

Physical Bongard Problems

Abstract : 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.
Document type :
Conference papers
Complete list of metadata

Cited literature [12 references]  Display  Hide  Download
Contributor : Hal Ifip Connect in order to contact the contributor
Submitted on : Thursday, May 11, 2017 - 5:10:47 PM
Last modification on : Thursday, March 5, 2020 - 5:41:40 PM
Long-term archiving on: : Saturday, August 12, 2017 - 1:59:10 PM


Files produced by the author(s)


Distributed under a Creative Commons Attribution 4.0 International License



Erik Weitnauer, Helge Ritter. Physical Bongard Problems. 8th International Conference on Artificial Intelligence Applications and Innovations (AIAI), Sep 2012, Halkidiki, Greece. pp.157-163, ⟨10.1007/978-3-642-33409-2_17⟩. ⟨hal-01521431⟩



Record views


Files downloads