The Localist and the Distributed Models of Connectionism

Abstract

Connectionism is the theory that sees brain in terms of neural or parallel distributed processing networks of interconnected units. The present paper reviewed the basic assumptions of connectionism and two main types of connectionist models were explained; the localist model and the distributed model. The drawbacks of the localist connectionism were mentioned. Properties of distributed connectionist networks were delineated. In the end, general problems with connectionist models were discussed.  It was mentioned that the major drawback of connectionism that would cast doubt on the usefulness of a connectionist approach was that this approach had its basis on the sciences of math and physics, while the brains of human beings, or language learners, are biological entities. This seems to mar the usefulness of this approach to language learning, since it can be hardly assumed that the mathematical principles can be extended to biological ones. Language learners, language teachers as well as neurologists and psychologists may find the discussions of the present study useful in the process of language acquisition.