Symmetry as an Organizing Principle for Geometric Intelligence
This work addresses geometric reasoning in AI, which is incremental as it builds on prior models with a symmetry-based approach.
The authors tackled the problem of geometric intelligence by developing an AI agent that uses symmetry as an organizing principle, achieving performance comparable to existing AI models on Dehaene's test and showing correlation with human behavior.
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.