Linked Life Data

10473846

Source:http://linkedlifedata.com/resource/pubmed/id/10473846

Statements in which the resource exists as a subject.
PredicateObject
rdf:type
lifeskim:mentions
pubmed:issue
3
pubmed:dateCreated
1999-11-2
pubmed:abstractText
While learning and development are well characterized in feedforward networks, these features are more difficult to analyze in recurrent networks due to the increased complexity of dual dynamics - the rapid dynamics arising from activation states and the slow dynamics arising from learning or developmental plasticity. We present analytical and numerical results that consider dual dynamics in a recurrent network undergoing Hebbian learning with either constant weight decay or weight normalization. Starting from initially random connections, the recurrent network develops symmetric or near-symmetric connections through Hebbian learning. Reciprocity and modularity arise naturally through correlations in the activation states. Additionally, weight normalization may be better than constant weight decay for the development of multiple attractor states that allow a diverse representation of the inputs. These results suggest a natural mechanism by which synaptic plasticity in recurrent networks such as cortical and brainstem premotor circuits could enhance neural computation and the generation of motor programs.
pubmed:grant
pubmed:language
eng
pubmed:journal
pubmed:citationSubset
IM
pubmed:status
MEDLINE
pubmed:month
Sep
pubmed:issn
0340-1200
pubmed:author
pubmed:issnType
Print
pubmed:volume
81
pubmed:owner
NLM
pubmed:authorsComplete
Y
pubmed:pagination
211-25
pubmed:dateRevised
2007-11-14
pubmed:meshHeading
pubmed:year
1999
pubmed:articleTitle
Emergence of symmetric, modular, and reciprocal connections in recurrent networks with Hebbian learning.
pubmed:affiliation
Department of Physiology M211, Northwestern University Medical School, 303 East Chicago Avenue, Chicago, IL 60611 3008, USA.
pubmed:publicationType
Journal Article, Research Support, U.S. Gov't, P.H.S.