Learning and disrupting invariance in visual recognition
Learning by temporal association rules such as Foldiak's trace rule is an attractive hypothesis that explains the development of invariance in visual recognition. Consistent with these rules, several recent experiments have shown that invariance can be broken by appropriately altering the visua...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Language: | en-US |
| Published: |
2011
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/65646 |
| _version_ | 1811081155280109568 |
|---|---|
| author | Isik, Leyla Leibo, Joel Z Poggio, Tomaso |
| author2 | Tomaso Poggio |
| author_facet | Tomaso Poggio Isik, Leyla Leibo, Joel Z Poggio, Tomaso |
| author_sort | Isik, Leyla |
| collection | MIT |
| description | Learning by temporal association rules such as Foldiak's trace rule is an attractive hypothesis that explains the development of invariance in visual recognition. Consistent with these rules, several recent experiments have shown that invariance can be broken by appropriately altering the visual environment but found puzzling differences in the effects at the psychophysical versus single cell level. We show a) that associative learning provides appropriate invariance in models of object recognition inspired by Hubel and Wiesel b) that we can replicate the "invariance disruption" experiments using these models with a temporal association learning rule to develop and maintain invariance, and c) that we can thereby explain the apparent discrepancies between psychophysics and singe cells effects. We argue that these models account for the stability of perceptual invariance despite the underlying plasticity of the system, the variability of the visual world and expected noise in the biological mechanisms. |
| first_indexed | 2024-09-23T11:42:21Z |
| id | mit-1721.1/65646 |
| institution | Massachusetts Institute of Technology |
| language | en-US |
| last_indexed | 2024-09-23T11:42:21Z |
| publishDate | 2011 |
| record_format | dspace |
| spelling | mit-1721.1/656462019-11-22T04:17:38Z Learning and disrupting invariance in visual recognition Isik, Leyla Leibo, Joel Z Poggio, Tomaso Tomaso Poggio Center for Biological and Computational Learning (CBCL) vision, object recognition Learning by temporal association rules such as Foldiak's trace rule is an attractive hypothesis that explains the development of invariance in visual recognition. Consistent with these rules, several recent experiments have shown that invariance can be broken by appropriately altering the visual environment but found puzzling differences in the effects at the psychophysical versus single cell level. We show a) that associative learning provides appropriate invariance in models of object recognition inspired by Hubel and Wiesel b) that we can replicate the "invariance disruption" experiments using these models with a temporal association learning rule to develop and maintain invariance, and c) that we can thereby explain the apparent discrepancies between psychophysics and singe cells effects. We argue that these models account for the stability of perceptual invariance despite the underlying plasticity of the system, the variability of the visual world and expected noise in the biological mechanisms. 2011-09-12T16:00:13Z 2011-09-12T16:00:13Z 2011-09-10 http://hdl.handle.net/1721.1/65646 en-US MIT-CSAIL-TR-2011-040 CBCL-302 Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported http://creativecommons.org/licenses/by-nc-nd/3.0/ 13 p. application/pdf |
| spellingShingle | vision, object recognition Isik, Leyla Leibo, Joel Z Poggio, Tomaso Learning and disrupting invariance in visual recognition |
| title | Learning and disrupting invariance in visual recognition |
| title_full | Learning and disrupting invariance in visual recognition |
| title_fullStr | Learning and disrupting invariance in visual recognition |
| title_full_unstemmed | Learning and disrupting invariance in visual recognition |
| title_short | Learning and disrupting invariance in visual recognition |
| title_sort | learning and disrupting invariance in visual recognition |
| topic | vision, object recognition |
| url | http://hdl.handle.net/1721.1/65646 |
| work_keys_str_mv | AT isikleyla learninganddisruptinginvarianceinvisualrecognition AT leibojoelz learninganddisruptinginvarianceinvisualrecognition AT poggiotomaso learninganddisruptinginvarianceinvisualrecognition |