The computational magic of the ventral stream: sketch of a theory (and why some deep architectures work).

Author(s)
Poggio, Tomaso; Mutch, Jim; Leibo, Joel; Rosasco, Lorenzo; Tacchetti, Andrea
Thumbnail
DownloadMIT-CSAIL-TR-2012-035.pdf (5.305Mb)
Other Contributors
Center for Biological and Computational Learning (CBCL)
Advisor
Tomaso Poggio
Terms of use
Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported http://creativecommons.org/licenses/by-nc-nd/3.0/
Metadata
Show full item record
Abstract
This paper explores the theoretical consequences of a simple assumption: the computational goal of the feedforward path in the ventral stream -- from V1, V2, V4 and to IT -- is to discount image transformations, after learning them during development.
Date issued
2012-12-29
URI
http://hdl.handle.net/1721.1/76248
Series/Report no.
MIT-CSAIL-TR-2012-035
Keywords
visual cortex, ventral stream, symmetries principles in sensory perception, visual recognition, invariances of sensory perception, learning to learn invariants in the visual world
Collections

The following license files are associated with this item: