Accelerated-Learning-Online.com - helping you learn faster
Home | Contact Us
Search Site:
 
Home
Learning State
Learning Process
Memory Techniques
Learning Styles
Learning Approach
Learning Challenges
Other Resources
Research Articles
Brain News
Contact Us

Research article summary:

Challenging the widespread assumption that connectionism and distributed representations go hand-in-hand.

Abstract Extract:
One of the central claims associated with the parallel distributed processing approach popularized by D.E. Rumelhart, J.L. McClelland and the PDP Research Group is that knowledge is coded in a distributed fashion. Localist representations within this ... (Full abstract text below)

Published 2002Nov in Journal: Cognit Psychol (Language : eng)

Full Pubmed Extract

This information was retrieved, real-time, on your behalf from the public area of the Pubmed website:

1. Cognit Psychol. 2002 Nov;45(3):413-45

Challenging the widespread assumption that connectionism and distributed representations go hand-in-hand.

Bowers JS

Department of Experimental Psychology, University of Bristol, BS8-1TN, Bristol, UK. j.bowers@bris.ac.uk

One of the central claims associated with the parallel distributed processing approach popularized by D.E. Rumelhart, J.L. McClelland and the PDP Research Group is that knowledge is coded in a distributed fashion. Localist representations within this perspective are widely rejected. It is important to note, however, that connectionist networks can learn localist representations and many connectionist models depend on localist coding for their functioning. Accordingly, a commitment to distributed representations should be considered a specific theoretical claim regarding the structure of knowledge rather than a core principle, as often assumed. In this paper, it is argued that there are fundamental computational and empirical challenges that have not yet been addressed by distributed connectionist theories that are readily accommodated within localist approaches. This is highlighted in the context of modeling word and nonword naming, the domain in which some of the strongest claims have been made. It is shown that current PDP models provide a poor account of naming monosyllable items, and that distributed representations make it difficult for these models to scale up to more complex language phenomena. At the same time, models that learn localist representations are shown to hold promise in supporting many of the core reading and language functions on which PDP models fail. It is concluded that the common rejection of localist coding schemes within connectionist architectures is premature.

PMID : 12480480 [PubMed - Indexed for MEDLINE]


This information is obtained from the National Library of Medicine (NLM). Abstract text and other information may be subject to copyright. Type "NLM copyright" into Google for more information.

Full Author Information

First NameLastNameInitials
Jeffrey SBowersJS

Affiliation: Department of Experimental Psychology, University of Bristol, BS8-1TN, Bristol, UK. j.bowers@bris.ac.uk

3rd Party provider links

Click the links below to go to related 3rd party information:

MESH categories and related page links

This article was linked to the MESH categories shown on the left below. The links on the right are related Memletics pages.

Category links from this article:

   

Related Memletics topics:

Links for this article

For links to places where you can get the full text of this article see links. Note there may be a subscription or fee required for access to the full text.

New! Using similar technology to this site, we have launched find-health-articles.com, targeting over 1 million health research article abstracts.

Related Articles

Here are some articles related to this one (by title keywords):

Keywords in this article:

accommodated, accordingly, account, addressed, approach, approaches, architectures, argued, associated, assumed, central, challenges, claims, coded, coding, commitment, common, complex, computational, concluded, connectionist, considered, context, core, current, depend, difficult, distributed, domain, empirical, fail, fashion, functioning, functions, fundamental, group, highlighted, hold, important, items, j, knowledge, language, learn, localist, many, mcclelland, modeling, models, monosyllable, more, naming, networks, nonword, note, one, paper, parallel, pdp, perspective, phenomena, poor, popularized, principle, processing, promise, provide, readily, reading, rejected, rejection, representations, research, rumelhart, same, scale, schemes, specific, strongest, structure, supporting, theoretical, theories, time, widely, word, yet

Also, see our new free speed reading online course (beta version)

© Advanogy.com 2003-2007 - All rights reserved. Terms of Use | Privacy Statement | Contact Us