Proceedings of the Annual Meeting of the Cognitive Science Society

In this study, the printing forms (different fonts) of about 3000 common Chinese characters were sent into a Deep NeuralNetwork (DNN), along with their sounds. The network can successfully learn the association between the form and thesound of these characters. It also develops certain generalizability when facing new characters. In addition, the internalrepresentations on different layers of the network show the emergence of basic writing structures of Chinese characters(i.e. strokes, radicals, left-right, top-down structures ). The learning pattern of the network is further compared with thatof the elementary school students.