?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=Neural+coding+strategies+and+mechanisms+of+competition&rft.creator=Spratling%2C+Dr+M+W&rft.creator=Johnson%2C+Prof+M+H&rft.subject=Neural+Modelling&rft.subject=Neural+Nets&rft.description=A+long+running+debate+has+concerned+the+question+of+whether+neural%0Arepresentations+are+encoded+using+a+distributed+or+a+local+coding+scheme.++In%0Aboth+schemes+individual+neurons+respond+to+certain+specific+patterns+of%0Apre-synaptic+activity.++Hence%2C+rather+than+being+dichotomous%2C+both+coding%0Aschemes+are+based+on+the+same+representational+mechanism.++We+argue+that+a%0Apopulation+of+neurons+needs+to+be+capable+of+learning+both+local+and+distributed%0Arepresentations%2C+as+appropriate+to+the+task%2C+and+should+be+capable+of+generating%0Aboth+local+and+distributed+codes+in+response+to+different+stimuli.++Many+neural%0Anetwork+algorithms%2C+which+are+often+employed+as+models+of+cognitive+processes%2C%0Afail+to+meet+all+these+requirements.+In+contrast%2C+we+present+a+neural+network%0Aarchitecture+which+enables+a+single+algorithm+to+efficiently+learn%2C+and+respond%0Ausing%2C+both+types+of+coding+scheme.%0A&rft.date=2004&rft.type=Journal+(Paginated)&rft.type=PeerReviewed&rft.format=application%2Fpdf&rft.identifier=http%3A%2F%2Fcogprints.org%2F3541%2F1%2Fcogsysres.pdf&rft.identifier=++Spratling%2C+Dr+M+W+and+Johnson%2C+Prof+M+H++(2004)+Neural+coding+strategies+and+mechanisms+of+competition.++%5BJournal+(Paginated)%5D+++++&rft.relation=http%3A%2F%2Fcogprints.org%2F3541%2F