Physical Bongard Problems

@inproceedings{Weitnauer2012PhysicalBP,
  title={Physical Bongard Problems},
  author={Erik Weitnauer and Helge J. Ritter},
  booktitle={AIAI},
  year={2012}
}
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… 
A Semantic Web-based Representation of Human-logical Inference for Solving Bongard Problems
TLDR
The results demonstrated that the proposed model not only provided individual solutions as a BP solver, but also proved the correctness of Hofstadter's idea as the flexible frame with concept networks for BPs in the actual implementation, which no one has ever achieved.
A Computational Model for Learning Structured Concepts From Physical Scenes
TLDR
This work presents a novel computational model that perceives and learns structured concepts from physical scenes and finds that these manipulations affect the algorithm similarly to human participants that worked on the same task.
Physical problem solving: Joint planning with symbolic, geometric, and dynamic constraints
TLDR
A model is developed that plans over a symbolic representation of the situation, executes the plan using a geometric solver, and checks the plan's feasibility by taking into account the physical constraints of the scene.
Merced Proceedings of the Annual Meeting of the Cognitive Science Society Title Grouping 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
A Situated Dialogue System for Learning Structural Concepts in Blocks World
We present a modular, end-to-end dialogue system for a situated agent to address a multimodal, natural language dialogue task in which the agent learns complex representations of block structure
Similarity-based Ordering of Instances for Efficient Concept Learning
TLDR
This paper uses Physical Bongard Prob- lems, a rich categorization task with an open feature space, to analyze the combined effects of comparing dissimilar and similar instances within and across categories and shows that grouping instances to promote dissimilar within- and between- category comparisons improves the learning results.
Artificial General Intelligence: 13th International Conference, AGI 2020, St. Petersburg, Russia, September 16–19, 2020, Proceedings
TLDR
By proving that a certain measure (arguably an intelligence measure) decreases when an idealized parent AGI single-handedly creates a child AGI, it is argued that a similar Law holds for AGIs.
Grouping by Similarity Helps Concept Learning
TLDR
A manipulation of the similarity of instances shown temporally close to each other with blocked and interleaved presentation indicates a stronger effect of similarity on interleaving than on blocking, and shows a large benefit of com- paring similar between-category instances on concept learning tasks where the feature dimensions are not known in advance but have to be constructed.
Does vocabulary help structure the mind?
Does language reflect the categories of our mind or does it help create them? On one widespread view (cognitive priority), learning a language involves mapping words onto pre-existing categories,
Analyzing Elementary School Olympiad Math Tasks as a Benchmark for AGI
Many benchmarks and challenges for AI and AGI exist, which help to reveal both short- and long-term topics and directions of research. We analyze elementary school Olympiad math tasks as a possible
...
1
2
...

References

SHOWING 1-10 OF 15 REFERENCES
Generalization as Search
Abstract The problem of concept learning, or forming a general description of a class of objects given a set of examples and non-examples, is viewed here as a search problem. Existing programs that
Manual Intelligence as a Rosetta Stone for Robot Cognition
TLDR
This work envisage manual intelligence as a “Rosetta stone” for robot cognition, and presents and discusses some of the manifold connections between manual actions and cognitive functions.
Qualitative Process Theory: Twelve Years After
TLDR
This essay summarizes the context of that work and the main contributions of QP theory and encompasses a variety of tasks and skills, thus providing a range of interesting problems.
Computational models of analogy.
TLDR
Analogical mapping is a core process in human cognition, and there is now considerable consensus regarding the constraints governing the mapping process, but computational models still differ in their focus.
Interpreting Schematic Sketches Using Physical Reasoning
TLDR
A program that uses both geometric and physical reasoning to interpret schematic sketches of physical devices, able to disambiguate the meanings of the individual symbols and produce a natural language description of how the sketched device would operate.
A Rational Analysis of Rule-Based Concept Learning
TLDR
A new model of human concept learning that provides a rational analysis of learning feature-based concepts is proposed, built upon Bayesian inference for a grammatically structured hypothesis space-a concept language of logical rules.
DL-Learner: Learning Concepts in Description Logics
TLDR
DL-Learner is a framework for learning in description logics and OWL, a cross-platform framework implemented in Java that allows easy programmatic access and provides a command line interface, a graphical interface as well as a WSDL-based web service.
Pattern Recognition
Physical bongard problems
  • http://naive-physics.com/pbp/
  • 2012
Physical bongard problems (2012), http://naive-physics.com/pbp
  • 2012
...
1
2
...