Solving Bongard Problems with a Visual Language and Pragmatic Reasoning

by   Stefan Depeweg, et al.

More than 50 years ago Bongard introduced 100 visual concept learning problems as a testbed for intelligent vision systems. These problems are now known as Bongard problems. Although they are well known in the cognitive science and AI communities only moderate progress has been made towards building systems that can solve a substantial subset of them. In the system presented here, visual features are extracted through image processing and then translated into a symbolic visual vocabulary. We introduce a formal language that allows representing complex visual concepts based on this vocabulary. Using this language and Bayesian inference, complex visual concepts can be induced from the examples that are provided in each Bongard problem. Contrary to other concept learning problems the examples from which concepts are induced are not random in Bongard problems, instead they are carefully chosen to communicate the concept, hence requiring pragmatic reasoning. Taking pragmatic reasoning into account we find good agreement between the concepts with high posterior probability and the solutions formulated by Bongard himself. While this approach is far from solving all Bongard problems, it solves the biggest fraction yet.


page 1

page 2

page 3

page 4


Interpretable Visual Reasoning via Induced Symbolic Space

We study the problem of concept induction in visual reasoning, i.e., ide...

A Concept Learning Approach to Multisensory Object Perception

This paper presents a computational model of concept learning using Baye...

Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning

Humans have an inherent ability to learn novel concepts from only a few ...

"This is my unicorn, Fluffy": Personalizing frozen vision-language representations

Large Vision Language models pretrained on web-scale data provide re...

Modeling Human-like Concept Learning with Bayesian Inference over Natural Language

We model learning of abstract symbolic concepts by performing Bayesian i...

Concept Learning with Energy-Based Models

Many hallmarks of human intelligence, such as generalizing from limited ...

Characterizing an Analogical Concept Memory for Architectures Implementing the Common Model of Cognition

Architectures that implement the Common Model of Cognition - Soar, ACT-R...

Please sign up or login with your details

Forgot password? Click here to reset