On Invariance and Selectivity in Representation Learning

TitleOn Invariance and Selectivity in Representation Learning
Publication TypeCBMM Memos
Year of Publication2015
AuthorsAnselmi, F, Rosasco, L, Poggio, T
Number029
Date Published03/23/2015
Publication LanguageEnglish
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.

arXiv

arXiv:1503.05938v1

DSpace@MIT

http://hdl.handle.net/1721.1/100194

Download:  PDF icon CBMM Memo No. 029
CBMM Memo No:  029

Research Area: 

CBMM Relationship: 

  • CBMM Funded