Abstract

Multiple explanatory frameworks may be required to provide an adequate account of human cognition. This paper embeds the classical account within a neural network framework, exploring the encoding of syntactically-structured objects over the synchronic-diachronic characteristics of networks. Synchronic structure is defined in terms of temporal binding and the superposition of states. To accommodate asymmetric relations, synchronic structure is subject to the type uniqueness constraint (TUC). The nature of synchronic structure is shown to underlie X-bar theory that characterizes the phrasal structure of human languages. The derivation differentiates core X-bar properties from language-specific properties.