Routledge Dictionary of Language and Linguistics
Paradigm of research in artificial intelligence that is oriented towards neurology. In contrast to the symbolic processing method of traditional artificial intelligence that uses sequential, globally directed processes, in connectionism processing takes place through numerous local and highly parallel processes. Recent debate between adherents of connectionism and its challengers has centered on whether connectionist approaches represent an alternative to or a complement of symbolic information processing, which is based on the fundamental concepts of rule and representations, eschewed in connectionism.
References.
Elman, J.L. 1993. Learning and development in neural networks: the importance of starting small. Cognition 48. 71–99.
Mikkulainen, R. 1993. Subsymbolic natural language processes. Cambridge, MA.
Pinker, S. and J.Mehler (eds) 1988. Cognition 28: 1-2 (special issue).
Plunkett, K.
and V.Marchman. 1991. U-shaped learning and frequency effects in a multi-layered perceptron: Implications for child language acquisition. Cognition 38. 43–102.
——1993. From rote learning to system building: acquiring verb morphology in children and connectionist nets. Cognition 48. 21–69.
Rumelhart, D. and E.J.McClelland. 1986. Parallel distributed processing, 2 vols. Cambridge, MA.
This is the complete article, containing 170 words
(approx. 1 page at 300 words per page).
View More Summaries on Connectionism
