Abstract and Keywords
Connectionism is a computational modeling framework inspired by the principles of information processing that characterize biological neural systems, which rely on collections of simple processing units linked together into networks. These units communicate in parallel via connections of varying strength that can be modified by experience. Connectionist networks have a wide range of theoretical and practical applications because they exhibit sophisticated, flexible, and context-sensitive behavior that mirrors human cognitive performance in many domains, from perception to language processing. By emphasizing the commonalities underlying various cognitive abilities, connectionism considers how a basic set of computational principles might give rise to many different forms of complex behavior. Thus connectionism supports a novel way of thinking about the nature and origins of mental life, as the emergent consequence of a system based around principles of parallel processing, distributed representation, and statistical learning that interacts with its environment over the course of development.
Access to the complete content on Oxford Handbooks Online requires a subscription or purchase. Public users are able to search the site and view the abstracts and keywords for each book and chapter without a subscription.
If you have purchased a print title that contains an access token, please see the token for information about how to register your code.