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...

Full description

Bibliographic Details
Main Authors: Bouvrie, Jacob Vincent, Rosasco, Lorenzo Andrea, Poggio, Tomaso A., Smale, S., Caponnetto, A.
Other Authors: Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Format: Article
Language:en_US
Published: Springer-Verlag 2013
Online Access:http://hdl.handle.net/1721.1/76632
https://orcid.org/0000-0002-3944-0455
https://orcid.org/0000-0001-6376-4786
https://orcid.org/0000-0001-6008-7417
_version_ 1826188796764356608
author Bouvrie, Jacob Vincent
Rosasco, Lorenzo Andrea
Poggio, Tomaso A.
Smale, S.
Caponnetto, A.
author2 Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
author_facet Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Bouvrie, Jacob Vincent
Rosasco, Lorenzo Andrea
Poggio, Tomaso A.
Smale, S.
Caponnetto, A.
author_sort Bouvrie, Jacob Vincent
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 2024-09-23T08:04:50Z
format Article
id mit-1721.1/76632
institution Massachusetts Institute of Technology
language en_US
last_indexed 2024-09-23T08:04:50Z
publishDate 2013
publisher Springer-Verlag
record_format dspace
spelling mit-1721.1/766322022-09-30T07:21:13Z Mathematics of the Neural Response Bouvrie, Jacob Vincent Rosasco, Lorenzo Andrea Poggio, Tomaso A. Smale, S. Caponnetto, A. Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences McGovern Institute for Brain Research at MIT Poggio, Tomaso Bouvrie, Jacob Vincent Rosasco, Lorenzo Andrea Poggio, Tomaso A. 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. 2013-01-29T21:32:58Z 2013-01-29T21:32:58Z 2009-06 2009-05 Article http://purl.org/eprint/type/JournalArticle 1615-3375 1615-3383 http://hdl.handle.net/1721.1/76632 Smale, S. et al. “Mathematics of the Neural Response.” Foundations of Computational Mathematics 10.1 (2009): 67–91. https://orcid.org/0000-0002-3944-0455 https://orcid.org/0000-0001-6376-4786 https://orcid.org/0000-0001-6008-7417 en_US http://dx.doi.org/10.1007/s10208-009-9049-1 Foundations of Computational Mathematics Creative Commons Attribution-Noncommercial-Share Alike 3.0 http://creativecommons.org/licenses/by-nc-sa/3.0/ application/pdf Springer-Verlag Kathleen Sullivan
spellingShingle Bouvrie, Jacob Vincent
Rosasco, Lorenzo Andrea
Poggio, Tomaso A.
Smale, S.
Caponnetto, A.
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
url http://hdl.handle.net/1721.1/76632
https://orcid.org/0000-0002-3944-0455
https://orcid.org/0000-0001-6376-4786
https://orcid.org/0000-0001-6008-7417
work_keys_str_mv AT bouvriejacobvincent mathematicsoftheneuralresponse
AT rosascolorenzoandrea mathematicsoftheneuralresponse
AT poggiotomasoa mathematicsoftheneuralresponse
AT smales mathematicsoftheneuralresponse
AT caponnettoa mathematicsoftheneuralresponse