Main content



Loading wiki pages...

Wiki Version:
This repository contains clean bitmaps of the original 100 Bongard problems and code for a system that can solve around 35 of them. The code accompanies the following publication: [Depeweg, S., Rothkopf, C.A., Jäkel, F. (2024). Solving Bongard Problems with a Visual Language and Pragmatic Constraints. *Cognitive Science*, 48(5), e13432.][1] The system works by extracting visual predicates through standard image processing and then translating them into a symbolic visual vocabulary. With a visual grammar we can represent compositional visual concepts based on this vocabulary. Using this language and Bayesian inference, concepts can be induced from the examples that are provided in each problem. This is done by sampling from the posterior using Metropolis-Hastings. [1]:
OSF does not support the use of Internet Explorer. For optimal performance, please switch to another browser.
This website relies on cookies to help provide a better user experience. By clicking Accept or continuing to use the site, you agree. For more information, see our Privacy Policy and information on cookie use.

Start managing your projects on the OSF today.

Free and easy to use, the Open Science Framework supports the entire research lifecycle: planning, execution, reporting, archiving, and discovery.