?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=Learning+viewpoint+invariant+perceptual+representations+from+cluttered+images&rft.creator=Spratling%2C+Dr+Michael&rft.subject=Neural+Modelling&rft.subject=Machine+Vision&rft.subject=Neural+Nets&rft.description=In+order+to+perform+object+recognition%2C+it+is+necessary+to+form+perceptual+representations+that+are+sufficiently+specific+to+distinguish+between+objects%2C+but+that+are+also+sufficiently+flexible+to+generalise+across+changes+in+location%2C+rotation+and+scale.+A+standard+method+for+learning+perceptual+representations+that+are+invariant+to+viewpoint+is+to+form+temporal+associations+across+image+sequences+showing+object+transformations.+However%2C+this+method+requires+that+individual+stimuli+are+presented+in+isolation+and+is+therefore+unlikely+to+succeed+in+real-world+applications+where+multiple+objects+can+co-occur+in+the+visual+input.+This+article+proposes+a+simple+modification+to+the+learning+method%2C+that+can+overcome+this+limitation%2C+and+results+in+more+robust+learning+of+invariant+representations.%0A&rft.date=2005&rft.type=Journal+(Paginated)&rft.type=PeerReviewed&rft.format=application%2Fpdf&rft.identifier=http%3A%2F%2Fcogprints.org%2F4884%2F1%2Ftpami05.pdf&rft.identifier=++Spratling%2C+Dr+Michael++(2005)+Learning+viewpoint+invariant+perceptual+representations+from+cluttered+images.++%5BJournal+(Paginated)%5D+++++&rft.relation=http%3A%2F%2Fcogprints.org%2F4884%2F