Visual-Imagery-Based Analogical Construction in Geometric Matrix Reasoning Task
Yuan Yang, Keith McGreggor, Maithilee Kunda

TL;DR
This paper introduces computational models that use analogies and image transformations to solve Raven's Progressive Matrices, achieving high accuracy and demonstrating the effectiveness of visual-analogy approaches in geometric reasoning tasks.
Contribution
The paper presents novel computational models employing analogy and image transformation strategies for solving RPM problems, with high success rates on standard tests.
Findings
Solved 57 out of 60 RPM problems using proposed models
Analogies and image transformations are effective in geometric reasoning
Models follow strategies similar to human test-takers
Abstract
Raven's Progressive Matrices is a family of classical intelligence tests that have been widely used in both research and clinical settings. There have been many exciting efforts in AI communities to computationally model various aspects of problem solving such figural analogical reasoning problems. In this paper, we present a series of computational models for solving Raven's Progressive Matrices using analogies and image transformations. We run our models following three different strategies usually adopted by human testees. These models are tested on the standard version of Raven's Progressive Matrices, in which we can solve 57 out 60 problems in it. Therefore, analogy and image transformation are proved to be effective in solving RPM problems.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsCognitive Science and Mapping
