Mathematics of the Neural Response
We propose a natural image representation, the neural response, motivated by the neuroscience of the visual cortex. The inner product defined by the neural response leads to a similarity measure between functions which we call the derived kernel. Based on a hierarchical architecture, we give a recur...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Published: |
2008
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/43713 |
| _version_ | 1826214814639194112 |
|---|---|
| author | Caponnetto, Andrea Poggio, Tomaso Bouvrie, Jake Rosasco, Lorenzo Smale, Steve |
| author2 | Tomaso Poggio |
| author_facet | Tomaso Poggio Caponnetto, Andrea Poggio, Tomaso Bouvrie, Jake Rosasco, Lorenzo Smale, Steve |
| author_sort | Caponnetto, Andrea |
| collection | MIT |
| description | We propose a natural image representation, the neural response, motivated by the neuroscience of the visual cortex. The inner product defined by the neural response leads to a similarity measure between functions which we call the derived kernel. Based on a hierarchical architecture, we give a recursive definition of the neural response and associated derived kernel. The derived kernel can be used in a variety of application domains such as classification of images, strings of text and genomics data. |
| first_indexed | 2024-09-23T16:11:34Z |
| id | mit-1721.1/43713 |
| institution | Massachusetts Institute of Technology |
| last_indexed | 2024-09-23T16:11:34Z |
| publishDate | 2008 |
| record_format | dspace |
| spelling | mit-1721.1/437132019-04-11T00:32:22Z Mathematics of the Neural Response Caponnetto, Andrea Poggio, Tomaso Bouvrie, Jake Rosasco, Lorenzo Smale, Steve Tomaso Poggio Center for Biological and Computational Learning (CBCL) neuroscience computer vision kernels We propose a natural image representation, the neural response, motivated by the neuroscience of the visual cortex. The inner product defined by the neural response leads to a similarity measure between functions which we call the derived kernel. Based on a hierarchical architecture, we give a recursive definition of the neural response and associated derived kernel. The derived kernel can be used in a variety of application domains such as classification of images, strings of text and genomics data. 2008-11-27T01:30:05Z 2008-11-27T01:30:05Z 2008-11-26 http://hdl.handle.net/1721.1/43713 MIT-CSAIL-TR-2008-070 CBCL-276 25 p. application/pdf application/postscript |
| spellingShingle | neuroscience computer vision kernels Caponnetto, Andrea Poggio, Tomaso Bouvrie, Jake Rosasco, Lorenzo Smale, Steve Mathematics of the Neural Response |
| title | Mathematics of the Neural Response |
| title_full | Mathematics of the Neural Response |
| title_fullStr | Mathematics of the Neural Response |
| title_full_unstemmed | Mathematics of the Neural Response |
| title_short | Mathematics of the Neural Response |
| title_sort | mathematics of the neural response |
| topic | neuroscience computer vision kernels |
| url | http://hdl.handle.net/1721.1/43713 |
| work_keys_str_mv | AT caponnettoandrea mathematicsoftheneuralresponse AT poggiotomaso mathematicsoftheneuralresponse AT bouvriejake mathematicsoftheneuralresponse AT rosascolorenzo mathematicsoftheneuralresponse AT smalesteve mathematicsoftheneuralresponse |