Symmetry as an Organizing Principle for Geometric Intelligence

TL;DR

This paper introduces a computational approach that uses symmetry as a core principle to enhance geometric reasoning in AI agents, achieving performance comparable to existing models and aligning with human behavior.

Contribution

The paper presents a novel AI method leveraging symmetry as an organizing principle for geometric intelligence, addressing Dehaene's test.

Findings

Model performs on par with existing AI solutions.

Performance correlates with human behavior.

Symmetry-based approach enhances geometric reasoning.

Abstract

The exploration of geometrical patterns stimulates imagination and encourages abstract reasoning which is a distinctive feature of human intelligence. In cognitive science, Gestalt principles such as symmetry have often explained significant aspects of human perception. We present a computational technique for building artificial intelligence (AI) agents that use symmetry as the organizing principle for addressing Dehaene's test of geometric intelligence \cite{dehaene2006core}. The performance of our model is on par with extant AI models of problem solving on the Dehaene's test and seems correlated with some elements of human behavior on the same test.