Proceedings of the Annual Meeting of the Cognitive Science Society

People can often generalize concepts from just a single example, while machine learning algorithms typicallyrequire hundreds. Lake, Salakhutdinov and Tenenbaum (2016) studied this ability in the domain of handwritten characters,and proposed a model for one-shot learning of new concepts based on inferring compositionally structured generative models,and transfer (or learning to learn) from familiar concepts. Lake et al showed that their model fit well with the classifications anddrawings of adults, but provided no direct evidence for the role of learning to learn which presumably occurs mostly in childrenlearning to draw. Here we study the drawing and classification abilities of children ages 3-5, asking whether their ability toclassify novel objects and handwritten characters is related to their ability to infer an appropriate motor program for drawing ortracing characters. Preliminary results suggest at least a weak relationship between these abilities, independent of age.