Proceedings of the Annual Meeting of the Cognitive Science Society

In this study, we aim to understand the origins of human intuitions about Euclidean geometry by simulating geo-metric concepts acquisition with unsupervised learning in hierarchical generative models. Specifically, we build a deep neuralnetwork that learns a hierarchical generative model of sensory inputs. The results show that hidden layer activities can supportthe categorization of different geometric objects and distinguish among various spatial relationships between geometric figures.Specifically, hidden layer activities can be decoded to compare line orientations, detect right triangles, and judge whether twotriangles are similar or not. We further analyze the response profiles of hidden layers units and find some units resembling pari-etal neurons in the brain. Using unsupervised deep learning, the current modeling work provides a possible explanation of howEuclidean geometrical intuitions might emerge from daily visual experience, which has significant implications for cognitivepsychology and computational neuroscience.