Learning Transformation Invariance for Object Recognition

Jens Hocke; Thomas Martinetz

Learning Transformation Invariance for Object Recognition

Institut für Neuro- und Bioinformatik

Abstract

Based on Tomaso Poggio’sM-theory, we propose a method to learn transformation invariant representations. Using an artificial dataset, we demonstrate that our supervised method learns invariance to shifts, and on the MNIST data we show first results for learning the unknown transformations underlying handwritten digits.

Originalsprache	Englisch
Titel	Workshop New Challenges in Neural Computation 2014
Redakteure/-innen	Barbara Hammer, Thomas Villmann
Seitenumfang	6
Band	02
Erscheinungsdatum	02.09.2014
Seiten	20-25
Publikationsstatus	Veröffentlicht - 02.09.2014
Veranstaltung	36th German Conference on Pattern Recognition - Münster, Deutschland Dauer: 02.09.2014 → 05.09.2014 http://resources.mpi-inf.mpg.de/conferences/dagm/2014/workshops.html

UN SDGs

Dieser Output leistet einen Beitrag zu folgendem(n) Ziel(en) für nachhaltige Entwicklung

Dokumente

http://www.inb.uni-luebeck.de/publications/pdfs/HoMa14b.pdf

Weitere Links

https://www.techfak.uni-bielefeld.de/~fschleif/mlr/mlr.html

Zitieren

@inproceedings{febf23ffcddd437d96cbcbdd5ed1d7bd,

title = "Learning Transformation Invariance for Object Recognition",

abstract = "Based on Tomaso Poggio{\textquoteright}sM-theory, we propose a method to learn transformation invariant representations. Using an artificial dataset, we demonstrate that our supervised method learns invariance to shifts, and on the MNIST data we show first results for learning the unknown transformations underlying handwritten digits.",

author = "Jens Hocke and Thomas Martinetz",

year = "2014",

month = sep,

day = "2",

language = "English",

volume = "02",

series = "Machine Learning Reports",

pages = "20--25",

editor = "Barbara Hammer and Thomas Villmann",

booktitle = "Workshop New Challenges in Neural Computation 2014",

note = "36th German Conference on Pattern Recognition ; Conference date: 02-09-2014 Through 05-09-2014",

url = "http://resources.mpi-inf.mpg.de/conferences/dagm/2014/workshops.html",

}

TY - GEN

T1 - Learning Transformation Invariance for Object Recognition

AU - Hocke, Jens

AU - Martinetz, Thomas

PY - 2014/9/2

Y1 - 2014/9/2

N2 - Based on Tomaso Poggio’sM-theory, we propose a method to learn transformation invariant representations. Using an artificial dataset, we demonstrate that our supervised method learns invariance to shifts, and on the MNIST data we show first results for learning the unknown transformations underlying handwritten digits.

AB - Based on Tomaso Poggio’sM-theory, we propose a method to learn transformation invariant representations. Using an artificial dataset, we demonstrate that our supervised method learns invariance to shifts, and on the MNIST data we show first results for learning the unknown transformations underlying handwritten digits.

UR - https://www.techfak.uni-bielefeld.de/~fschleif/mlr/mlr.html

M3 - Conference contribution

VL - 02

T3 - Machine Learning Reports

SP - 20

EP - 25

BT - Workshop New Challenges in Neural Computation 2014

A2 - Hammer, Barbara

A2 - Villmann, Thomas

T2 - 36th German Conference on Pattern Recognition

Y2 - 2 September 2014 through 5 September 2014

ER -