Acquiring a Functionally Compositional System of Goal-Directed Actions of a Simulated Agent

We propose a sub-symbolic connectionist model in which a functionally compositional system self-organizes by learning a provided set of goaldirected actions. This approach is compatible with an idea taken from usagebased accounts of the developmental learning of language, especially one theory of infants’ acquisition process of symbols. The presented model potentially explains a possible continuous process underlying the transitions from rote knowledge to systematized knowledge by drawing an analogy to the formation process of a geometric regular arrangement of points. Based on the experimental results, the essential underlying process is discussed.