?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=Learning+Low+Dimensional+Representations+of+Visual+Objects+With+Extensive+Use+of+Prior+Knowledge&rft.creator=Intrator%2C+Nathan&rft.creator=Edelman%2C+Shimon&rft.subject=Cognitive+Psychology&rft.description=Learning+to+recognize+visual+objects+from+examples+requires+the+ability+to+find+meaningful+patterns+in+spaces+of+very+high+dimensionality.+We+present+a+method+for+dimensionality+reduction+which+effectively+biases+the+learning+system+by+combining+multiple+constraints+via+an+extensive+use+of+class+labels.+The+use+of+multiple+class+labels+steers+the+resulting+low-dimensional+representation+to+become+invariant+to+those+directions+of+variation+in+the+input+space+that+are+irrelevant+to+classification%3B+this+is+done+merely+by+making+class+labels+independent+of+these+directions.+We+also+show+that+prior+knowledge+of+the+proper+dimensionality+of+the+target+representation+can+be+imposed+by+training+a+multiple-layer+bottleneck+network.+A+series+of+computational+experiments+involving+parameterized+fractal+images+and+real+human+faces+indicate+that+the+low-dimensional+representation+extracted+by+our+method+leads+to+improved+generalization+in+the+learned+tasks%2C+and+is+likely+to+preserve+the+topology+of+the+original+space.&rft.date=1997&rft.type=Journal+(Paginated)&rft.type=PeerReviewed&rft.format=application%2Fpostscript&rft.identifier=http%3A%2F%2Fcogprints.org%2F563%2F2%2F199710005.ps&rft.identifier=++Intrator%2C+Nathan+and+Edelman%2C+Shimon++(1997)+Learning+Low+Dimensional+Representations+of+Visual+Objects+With+Extensive+Use+of+Prior+Knowledge.++%5BJournal+(Paginated)%5D++++(Unpublished)++&rft.relation=http%3A%2F%2Fcogprints.org%2F563%2F<script src='//archive-bar.soton.ac.uk/archive-bar.js'></script>