?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=A+self-organizing+neural+network+that+learns+to+detect+and+represent+visual+depth+from+occlusion+events&rft.creator=Marshall%2C+J.+A.&rft.creator=Alley%2C+R.+K.&rft.subject=Computational+Neuroscience&rft.subject=Artificial+Intelligence&rft.subject=Machine+Learning&rft.subject=Machine+Vision&rft.subject=Neural+Nets&rft.subject=Perceptual+Cognitive+Psychology&rft.description=Visual+occlusion+events+constitute+a+major+source+of+depth+information.+We+have+developed+a+neural+network+model+that+learns+to+detect+and+represent+depth+relations%2C+after+a+period+of+exposure+to+motion+sequences+containing+occlusion+and+disocclusion+events.+The+network's+learning+is+governed+by+a+new+set+of+learning+and+activation+rules.+The+network+develops+two+parallel+opponent+channels+or+%60%60chains''+of+lateral+excitatory+connections+for+every+resolvable+motion+trajectory.+One+channel%2C+the+%60%60On''+chain+or+%60%60visible''+chain%2C+is+activated+when+a+moving+stimulus+is+visible.+The+other+channel%2C+the+%60%60Off''+chain+or+%60%60invisible''+chain%2C+is+activated+when+a+formerly+visible+stimulus+becomes+invisible+due+to+occlusion.+The+On+chain+carries+a+predictive+modal+representation+of+the+visible+stimulus.+The+Off+chain+carries+a+persistent%2C+amodal+representation+that+predicts+the+motion+of+the+invisible+stimulus.+The+new+learning+rule+uses+disinhibitory+signals+emitted+from+the+On+chain+to+trigger+learning+in+the+Off+chain.+The+Off+chain+neurons+learn+to+interact+reciprocally+with+other+neurons+that+indicate+the+presence+of+occluders.+The+interactions+let+the+network+predict+the+disappearance+and+reappearance+of+stimuli+moving+behind+occluders%2C+and+they+let+the+unexpected+disappearance+or+appearance+of+stimuli+excite+the+representation+of+an+inferred+occluder+at+that+location.+Two+results+that+have+emerged+from+this+research+suggest+how+visual+systems+may+learn+to+represent+visual+depth+information.+First%2C+a+visual+system+can+learn+a+nonmetric+representation+of+the+depth+relations+arising+from+occlusion+events.+Second%2C+parallel+opponent+On+and+Off+channels+that+represent+both+modal+and+amodal+stimuli+can+also+be+learned+through+the+same+proce&rft.contributor=Bowyer%2C+K.W.&rft.contributor=Hall%2C+L.&rft.date=1993&rft.type=Conference+Paper&rft.type=NonPeerReviewed&rft.format=text%2Fhtml&rft.identifier=http%3A%2F%2Fcogprints.org%2F442%2F1%2Findex.html&rft.identifier=++Marshall%2C+J.+A.+and+Alley%2C+R.+K.++(1993)+A+self-organizing+neural+network+that+learns+to+detect+and+represent+visual+depth+from+occlusion+events.++%5BConference+Paper%5D+++++&rft.relation=http%3A%2F%2Fcogprints.org%2F442%2F