From primal templates to invariant recognition
We can immediately recognize novel objects seen only once before -- in different positions on the retina and at different scales (distances). Is this ability hardwired by our genes or learned during development -- and if so how? We present a computational proof that developmental learning of invar...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Published: |
2010
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/60216 |
| _version_ | 1826210246714982400 |
|---|---|
| author | Leibo, Joel Z Mutch, Jim Ullman, Shimon Poggio, Tomaso |
| author2 | Tomaso Poggio |
| author_facet | Tomaso Poggio Leibo, Joel Z Mutch, Jim Ullman, Shimon Poggio, Tomaso |
| author_sort | Leibo, Joel Z |
| collection | MIT |
| description | We can immediately recognize novel objects seen only once before -- in different positions on the retina and at different scales (distances). Is this ability hardwired by our genes or learned during development -- and if so how? We present a computational proof that developmental learning of invariance in recognition is possible and can emerge rapidly. This computational work sets the stage for experiments on the development of object invariance while suggesting a specific mechanism that may be critically tested. |
| first_indexed | 2024-09-23T14:46:46Z |
| id | mit-1721.1/60216 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T14:46:46Z |
| publishDate | 2010 |
| record_format | dspace |
| spelling | mit-1721.1/602162019-04-12T11:37:53Z From primal templates to invariant recognition Leibo, Joel Z Mutch, Jim Ullman, Shimon Poggio, Tomaso Tomaso Poggio Center for Biological and Computational Learning (CBCL) vision object recognition We can immediately recognize novel objects seen only once before -- in different positions on the retina and at different scales (distances). Is this ability hardwired by our genes or learned during development -- and if so how? We present a computational proof that developmental learning of invariance in recognition is possible and can emerge rapidly. This computational work sets the stage for experiments on the development of object invariance while suggesting a specific mechanism that may be critically tested. 2010-12-06T19:00:10Z 2010-12-06T19:00:10Z 2010-12-04 http://hdl.handle.net/1721.1/60216 MIT-CSAIL-TR-2010-057 CBCL-293 Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported http://creativecommons.org/licenses/by-nc-nd/3.0/ 4 p. application/pdf |
| spellingShingle | vision object recognition Leibo, Joel Z Mutch, Jim Ullman, Shimon Poggio, Tomaso From primal templates to invariant recognition |
| title | From primal templates to invariant recognition |
| title_full | From primal templates to invariant recognition |
| title_fullStr | From primal templates to invariant recognition |
| title_full_unstemmed | From primal templates to invariant recognition |
| title_short | From primal templates to invariant recognition |
| title_sort | from primal templates to invariant recognition |
| topic | vision object recognition |
| url | http://hdl.handle.net/1721.1/60216 |
| work_keys_str_mv | AT leibojoelz fromprimaltemplatestoinvariantrecognition AT mutchjim fromprimaltemplatestoinvariantrecognition AT ullmanshimon fromprimaltemplatestoinvariantrecognition AT poggiotomaso fromprimaltemplatestoinvariantrecognition |