On Invariance and Selectivity in Representation Learning
We discuss data representation which can be learned automatically from data, are invariant to transformations, and at the same time selective, in the sense that two points have the same representation only if they are one the transformation of the other. The mathematical results here sharpen some of...
| Main Authors: | , , |
|---|---|
| Format: | Technical Report |
| Language: | en_US |
| Published: |
Center for Brains, Minds and Machines (CBMM), arXiv
2015
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/100194 |
| _version_ | 1826212807896465408 |
|---|---|
| author | Anselmi, Fabio Rosasco, Lorenzo Poggio, Tomaso |
| author_facet | Anselmi, Fabio Rosasco, Lorenzo Poggio, Tomaso |
| author_sort | Anselmi, Fabio |
| collection | MIT |
| description | We discuss data representation which can be learned automatically from data, are invariant to transformations, and at the same time selective, in the sense that two points have the same representation only if they are one the transformation of the other. The mathematical results here sharpen some of the key claims of i-theory, a recent theory of feedforward processing in sensory cortex. |
| first_indexed | 2024-09-23T15:38:14Z |
| format | Technical Report |
| id | mit-1721.1/100194 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T15:38:14Z |
| publishDate | 2015 |
| publisher | Center for Brains, Minds and Machines (CBMM), arXiv |
| record_format | dspace |
| spelling | mit-1721.1/1001942019-04-12T12:31:30Z On Invariance and Selectivity in Representation Learning Anselmi, Fabio Rosasco, Lorenzo Poggio, Tomaso Invariance Representation Learning i-theory Sensory Cortex We discuss data representation which can be learned automatically from data, are invariant to transformations, and at the same time selective, in the sense that two points have the same representation only if they are one the transformation of the other. The mathematical results here sharpen some of the key claims of i-theory, a recent theory of feedforward processing in sensory cortex. This work was supported by the Center for Brains, Minds and Machines (CBMM), funded by NSF STC award CCF-1231216. 2015-12-11T21:42:05Z 2015-12-11T21:42:05Z 2015-03-23 Technical Report Working Paper Other http://hdl.handle.net/1721.1/100194 arXiv:1503.05938v1 en_US CBMM Memo Series;029 Attribution-NonCommercial 3.0 United States http://creativecommons.org/licenses/by-nc/3.0/us/ application/pdf Center for Brains, Minds and Machines (CBMM), arXiv |
| spellingShingle | Invariance Representation Learning i-theory Sensory Cortex Anselmi, Fabio Rosasco, Lorenzo Poggio, Tomaso On Invariance and Selectivity in Representation Learning |
| title | On Invariance and Selectivity in Representation Learning |
| title_full | On Invariance and Selectivity in Representation Learning |
| title_fullStr | On Invariance and Selectivity in Representation Learning |
| title_full_unstemmed | On Invariance and Selectivity in Representation Learning |
| title_short | On Invariance and Selectivity in Representation Learning |
| title_sort | on invariance and selectivity in representation learning |
| topic | Invariance Representation Learning i-theory Sensory Cortex |
| url | http://hdl.handle.net/1721.1/100194 |
| work_keys_str_mv | AT anselmifabio oninvarianceandselectivityinrepresentationlearning AT rosascolorenzo oninvarianceandselectivityinrepresentationlearning AT poggiotomaso oninvarianceandselectivityinrepresentationlearning |