Bringing the Grandmother Back into the Picture: A Memory-Based View of Object Recognition
We describe experiments with a versatile pictorial prototype based learning scheme for 3D object recognition. The GRBF scheme seems to be amenable to realization in biophysical hardware because the only kind of computation it involves can be effectively carried out by combining receptive fiel...
| Main Authors: | , |
|---|---|
| Language: | en_US |
| Published: |
2004
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/6011 |
| _version_ | 1811078047899582464 |
|---|---|
| author | Edelman, Shimon Poggio, Tomaso |
| author_facet | Edelman, Shimon Poggio, Tomaso |
| author_sort | Edelman, Shimon |
| collection | MIT |
| description | We describe experiments with a versatile pictorial prototype based learning scheme for 3D object recognition. The GRBF scheme seems to be amenable to realization in biophysical hardware because the only kind of computation it involves can be effectively carried out by combining receptive fields. Furthermore, the scheme is computationally attractive because it brings together the old notion of a "grandmother'' cell and the rigorous approximation methods of regularization and splines. |
| first_indexed | 2024-09-23T10:52:33Z |
| id | mit-1721.1/6011 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T10:52:33Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/60112019-04-10T17:24:43Z Bringing the Grandmother Back into the Picture: A Memory-Based View of Object Recognition Edelman, Shimon Poggio, Tomaso object recognition representation nonlinear interpolation sGrandmother cells We describe experiments with a versatile pictorial prototype based learning scheme for 3D object recognition. The GRBF scheme seems to be amenable to realization in biophysical hardware because the only kind of computation it involves can be effectively carried out by combining receptive fields. Furthermore, the scheme is computationally attractive because it brings together the old notion of a "grandmother'' cell and the rigorous approximation methods of regularization and splines. 2004-10-04T14:35:48Z 2004-10-04T14:35:48Z 1990-04-01 AIM-1181 http://hdl.handle.net/1721.1/6011 en_US AIM-1181 35 p. 4115113 bytes 1642873 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | object recognition representation nonlinear interpolation sGrandmother cells Edelman, Shimon Poggio, Tomaso Bringing the Grandmother Back into the Picture: A Memory-Based View of Object Recognition |
| title | Bringing the Grandmother Back into the Picture: A Memory-Based View of Object Recognition |
| title_full | Bringing the Grandmother Back into the Picture: A Memory-Based View of Object Recognition |
| title_fullStr | Bringing the Grandmother Back into the Picture: A Memory-Based View of Object Recognition |
| title_full_unstemmed | Bringing the Grandmother Back into the Picture: A Memory-Based View of Object Recognition |
| title_short | Bringing the Grandmother Back into the Picture: A Memory-Based View of Object Recognition |
| title_sort | bringing the grandmother back into the picture a memory based view of object recognition |
| topic | object recognition representation nonlinear interpolation sGrandmother cells |
| url | http://hdl.handle.net/1721.1/6011 |
| work_keys_str_mv | AT edelmanshimon bringingthegrandmotherbackintothepictureamemorybasedviewofobjectrecognition AT poggiotomaso bringingthegrandmotherbackintothepictureamemorybasedviewofobjectrecognition |