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.
| Identifer | oai:union.ndltd.org:MIT/oai:dspace.mit.edu:1721.1/6011 |
| Date | 01 April 1990 |
| Creators | Edelman, Shimon, Poggio, Tomaso |
| Source Sets | M.I.T. Theses and Dissertation |
| Language | en_US |
| Detected Language | English |
| Format | 35 p., 4115113 bytes, 1642873 bytes, application/postscript, application/pdf |
| Relation | AIM-1181 |
Page generated in 0.0024 seconds