Learning a selectivity--invariance--selectivity feature extraction architecture for images

M.U. Gutmann; A. Hyvärinen

Learning a selectivity--invariance--selectivity feature extraction architecture for images

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract / Description of output

Selectivity and invariance are thought to be important ingredients in biological or artificial visual systems. A fundamental problem is, however, to know what the visual system should be selective to and what to be nvariant to. Building a statistical model of images, we learn here a three-layer feature extraction system where the selectivity and invariance emerges from the properties of the images.

Original language	English
Title of host publication	Pattern Recognition (ICPR), 2012 21st International Conference on
Publisher	Institute of Electrical and Electronics Engineers
Pages	918-921
Number of pages	4
Publication status	Published - 2012

Access to Document

Gutmann2012bAccepted author manuscript, 238 KB

http://ieeexplore.ieee.org/document/6460284/?arnumber=6460284

Cite this

@inproceedings{07f618f362e74af0bf741c0be4423b24,

title = "Learning a selectivity--invariance--selectivity feature extraction architecture for images",

abstract = "Selectivity and invariance are thought to be important ingredients in biological or artificial visual systems. A fundamental problem is, however, to know what the visual system should be selective to and what to be nvariant to. Building a statistical model of images, we learn here a three-layer feature extraction system where the selectivity and invariance emerges from the properties of the images.",

author = "M.U. Gutmann and A. Hyv{\"a}rinen",

year = "2012",

language = "English",

pages = "918--921",

booktitle = "Pattern Recognition (ICPR), 2012 21st International Conference on",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

}

TY - GEN

T1 - Learning a selectivity--invariance--selectivity feature extraction architecture for images

AU - Gutmann, M.U.

AU - Hyvärinen, A.

PY - 2012

Y1 - 2012

N2 - Selectivity and invariance are thought to be important ingredients in biological or artificial visual systems. A fundamental problem is, however, to know what the visual system should be selective to and what to be nvariant to. Building a statistical model of images, we learn here a three-layer feature extraction system where the selectivity and invariance emerges from the properties of the images.

AB - Selectivity and invariance are thought to be important ingredients in biological or artificial visual systems. A fundamental problem is, however, to know what the visual system should be selective to and what to be nvariant to. Building a statistical model of images, we learn here a three-layer feature extraction system where the selectivity and invariance emerges from the properties of the images.

M3 - Conference contribution

SP - 918

EP - 921

BT - Pattern Recognition (ICPR), 2012 21st International Conference on

PB - Institute of Electrical and Electronics Engineers

ER -

Learning a selectivity--invariance--selectivity feature extraction architecture for images

Abstract / Description of output

Access to Document

Fingerprint

Cite this