On Invariance and Selectivity in Representation Learning
Name
CBMM-Memo-029.pdf
Size
812.07 KB
Format
Adobe PDF
Checksum (MD5)
b886de91bb6df70bc2d6f75396705c65
Author(s)
Anselmi, Fabio
Rosasco, Lorenzo
Poggio, Tomaso
Date Issued
March 23, 2015
Publisher
Center for Brains, Minds and Machines (CBMM), arXiv
Citation
arXiv:1503.05938v1
Series/Report no.
CBMM Memo Series;029
Abstract
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.
Subjects
Invariance
Representation Learning
i-theory
Sensory Cortex
Terms of Use
Attribution-NonCommercial 3.0 United States
Persistent DSpace Link
