Symmetry as a Representation of Intuitive Geometry?
This work addresses the challenge of understanding human cognitive processes in geometric pattern recognition, though it is incremental as it builds on prior symmetry-based models for related tests.
The paper tackled the problem of modeling human-like geometric intuition by developing a symmetry-based cognitive model for a 2-Alternative Forced Choice variation of the Core Geometry test, achieving accuracy comparable to the human average.
Recognition of geometrical patterns seems to be an important aspect of human intelligence. Geometric pattern recognition is used in many intelligence tests, including Dehaene's odd-one-out test of Core Geometry (CG)) based on intuitive geometrical concepts (Dehaene et al., 2006). Earlier work has developed a symmetry-based cognitive model of Dehaene's test and demonstrated performance comparable to that of humans. In this work, we further investigate the role of symmetry in geometrical intuition and build a cognitive model for the 2-Alternative Forced Choice (2-AFC) variation of the CG test (Marupudi & Varma 2021). In contrast to Dehaene's test, 2-AFC leaves almost no space for cognitive models based on generalization over multiple examples. Our symmetry-based model achieves an accuracy comparable to the human average on the 2-AFC test and appears to capture an essential part of intuitive geometry.