Spatial vs temporal continuity in view invariant visual object recognition learning.
We show in a 4-layer competitive neuronal network that continuous transformation learning, which uses spatial correlations and a purely associative (Hebbian) synaptic modification rule, can build view invariant representations of complex 3D objects. This occurs even when views of the different objec...
Main Authors: | , , |
---|---|
Format: | Journal article |
Language: | English |
Published: |
2006
|
_version_ | 1797070183696695296 |
---|---|
author | Perry, G Rolls, E Stringer, S |
author_facet | Perry, G Rolls, E Stringer, S |
author_sort | Perry, G |
collection | OXFORD |
description | We show in a 4-layer competitive neuronal network that continuous transformation learning, which uses spatial correlations and a purely associative (Hebbian) synaptic modification rule, can build view invariant representations of complex 3D objects. This occurs even when views of the different objects are interleaved, a condition where temporal trace learning fails. Human psychophysical experiments showed that view invariant object learning can occur when spatial but not temporal continuity applies because of interleaving of stimuli, although sequential presentation, which produces temporal continuity, can facilitate learning. Thus continuous transformation learning is an important principle that may contribute to view invariant object recognition. |
first_indexed | 2024-03-06T22:35:21Z |
format | Journal article |
id | oxford-uuid:59b3c346-5bcc-4b89-a069-45fe1bbba812 |
institution | University of Oxford |
language | English |
last_indexed | 2024-03-06T22:35:21Z |
publishDate | 2006 |
record_format | dspace |
spelling | oxford-uuid:59b3c346-5bcc-4b89-a069-45fe1bbba8122022-03-26T17:11:19ZSpatial vs temporal continuity in view invariant visual object recognition learning.Journal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:59b3c346-5bcc-4b89-a069-45fe1bbba812EnglishSymplectic Elements at Oxford2006Perry, GRolls, EStringer, SWe show in a 4-layer competitive neuronal network that continuous transformation learning, which uses spatial correlations and a purely associative (Hebbian) synaptic modification rule, can build view invariant representations of complex 3D objects. This occurs even when views of the different objects are interleaved, a condition where temporal trace learning fails. Human psychophysical experiments showed that view invariant object learning can occur when spatial but not temporal continuity applies because of interleaving of stimuli, although sequential presentation, which produces temporal continuity, can facilitate learning. Thus continuous transformation learning is an important principle that may contribute to view invariant object recognition. |
spellingShingle | Perry, G Rolls, E Stringer, S Spatial vs temporal continuity in view invariant visual object recognition learning. |
title | Spatial vs temporal continuity in view invariant visual object recognition learning. |
title_full | Spatial vs temporal continuity in view invariant visual object recognition learning. |
title_fullStr | Spatial vs temporal continuity in view invariant visual object recognition learning. |
title_full_unstemmed | Spatial vs temporal continuity in view invariant visual object recognition learning. |
title_short | Spatial vs temporal continuity in view invariant visual object recognition learning. |
title_sort | spatial vs temporal continuity in view invariant visual object recognition learning |
work_keys_str_mv | AT perryg spatialvstemporalcontinuityinviewinvariantvisualobjectrecognitionlearning AT rollse spatialvstemporalcontinuityinviewinvariantvisualobjectrecognitionlearning AT stringers spatialvstemporalcontinuityinviewinvariantvisualobjectrecognitionlearning |