Observations on Cortical Mechanisms for Object Recognition andsLearning
This paper sketches a hypothetical cortical architecture for visual 3D object recognition based on a recent computational model. The view-centered scheme relies on modules for learning from examples, such as Hyperbf-like networks. Such models capture a class of explanations we call Memory-Base...
| मुख्य लेखकों: | , |
|---|---|
| भाषा: | en_US |
| प्रकाशित: |
2004
|
| विषय: | |
| ऑनलाइन पहुंच: | http://hdl.handle.net/1721.1/7217 |
| _version_ | 1826196526394769408 |
|---|---|
| author | Poggio, Tomaso Hurlbert, Anya |
| author_facet | Poggio, Tomaso Hurlbert, Anya |
| author_sort | Poggio, Tomaso |
| collection | MIT |
| description | This paper sketches a hypothetical cortical architecture for visual 3D object recognition based on a recent computational model. The view-centered scheme relies on modules for learning from examples, such as Hyperbf-like networks. Such models capture a class of explanations we call Memory-Based Models (MBM) that contains sparse population coding, memory-based recognition, and codebooks of prototypes. Unlike the sigmoidal units of some artificial neural networks, the units of MBMs are consistent with the description of cortical neurons. We describe how an example of MBM may be realized in terms of cortical circuitry and biophysical mechanisms, consistent with psychophysical and physiological data. |
| first_indexed | 2024-09-23T10:28:44Z |
| id | mit-1721.1/7217 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T10:28:44Z |
| publishDate | 2004 |
| record_format | dspace |
| spelling | mit-1721.1/72172019-04-12T08:34:07Z Observations on Cortical Mechanisms for Object Recognition andsLearning Poggio, Tomaso Hurlbert, Anya object recognition IT cortex view invariance This paper sketches a hypothetical cortical architecture for visual 3D object recognition based on a recent computational model. The view-centered scheme relies on modules for learning from examples, such as Hyperbf-like networks. Such models capture a class of explanations we call Memory-Based Models (MBM) that contains sparse population coding, memory-based recognition, and codebooks of prototypes. Unlike the sigmoidal units of some artificial neural networks, the units of MBMs are consistent with the description of cortical neurons. We describe how an example of MBM may be realized in terms of cortical circuitry and biophysical mechanisms, consistent with psychophysical and physiological data. 2004-10-20T20:50:04Z 2004-10-20T20:50:04Z 1993-12-01 AIM-1404 CBCL-077 http://hdl.handle.net/1721.1/7217 en_US AIM-1404 CBCL-077 24 p. 272626 bytes 1060397 bytes application/octet-stream application/pdf application/octet-stream application/pdf |
| spellingShingle | object recognition IT cortex view invariance Poggio, Tomaso Hurlbert, Anya Observations on Cortical Mechanisms for Object Recognition andsLearning |
| title | Observations on Cortical Mechanisms for Object Recognition andsLearning |
| title_full | Observations on Cortical Mechanisms for Object Recognition andsLearning |
| title_fullStr | Observations on Cortical Mechanisms for Object Recognition andsLearning |
| title_full_unstemmed | Observations on Cortical Mechanisms for Object Recognition andsLearning |
| title_short | Observations on Cortical Mechanisms for Object Recognition andsLearning |
| title_sort | observations on cortical mechanisms for object recognition andslearning |
| topic | object recognition IT cortex view invariance |
| url | http://hdl.handle.net/1721.1/7217 |
| work_keys_str_mv | AT poggiotomaso observationsoncorticalmechanismsforobjectrecognitionandslearning AT hurlbertanya observationsoncorticalmechanismsforobjectrecognitionandslearning |