Cerebral and Cerebellar Models of Language Learning

Abstract

Recent research in ‘connectionism’ has awakened interest in parallel models of language. The most widely-reported architectures model cerebellar cortex. Language, however, is principally learned by cerebral cortex. In cerebral anatomies, Peircean ‘surprising events’ cause ‘rebounds’: revolutions in which dominant synergies of dipole fields (rules) are overthrown and replaced by new synergies. Grossberg's Adaptive Resonance Theory (ART) describes such anatomies. The ART model is presented as a general framework for explaining common linguistic phenomena such as fossilization, categorical perception, vowel phonemicization, and linguistic rule formation. The performance of cerebral ART models is compared with that of cerebellar models (Parallel Distributed Processing, Boltzmann machines). In conclusion, ART is proposed as a basis for unifying language learning theories with each other and with praxis.