An efficient algorithm for learning invariances in adaptive classifiers

P. Simard, Yann LeCun, J. Denker, B. Victorri

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In many machine learning applications, one has not only training data but also some high-level information about certain invariances that the system should exhibit. In character recognition, for example, the answer should be invariant with respect to small spatial distortions in the input images (translations, rotations, scale changes, etcetera). We have implemented a scheme that minimizes the derivative of the classifier outputs with respect to distortion operators of our choosing. This not only produces tremendous speed advantages, but also provides a powerful language for specifying what generalizations we wish the network to perform.

Original languageEnglish (US)
Title of host publicationConference B
Subtitle of host publicationPattern Recognition Methodology and Systems
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages651-655
Number of pages5
Volume2
ISBN (Print)0818629150
DOIs
StatePublished - Jan 1 1992
Event11th IAPR International Conference on Pattern Recognition, IAPR 1992 - The Hague, Netherlands
Duration: Aug 30 1992Sep 3 1992

Other

Other11th IAPR International Conference on Pattern Recognition, IAPR 1992
CountryNetherlands
CityThe Hague
Period8/30/929/3/92

Fingerprint

Invariance
Classifiers
Character recognition
Learning systems
Derivatives

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Simard, P., LeCun, Y., Denker, J., & Victorri, B. (1992). An efficient algorithm for learning invariances in adaptive classifiers. In Conference B: Pattern Recognition Methodology and Systems (Vol. 2, pp. 651-655). [201861] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPR.1992.201861

An efficient algorithm for learning invariances in adaptive classifiers. / Simard, P.; LeCun, Yann; Denker, J.; Victorri, B.

Conference B: Pattern Recognition Methodology and Systems. Vol. 2 Institute of Electrical and Electronics Engineers Inc., 1992. p. 651-655 201861.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Simard, P, LeCun, Y, Denker, J & Victorri, B 1992, An efficient algorithm for learning invariances in adaptive classifiers. in Conference B: Pattern Recognition Methodology and Systems. vol. 2, 201861, Institute of Electrical and Electronics Engineers Inc., pp. 651-655, 11th IAPR International Conference on Pattern Recognition, IAPR 1992, The Hague, Netherlands, 8/30/92. https://doi.org/10.1109/ICPR.1992.201861
Simard P, LeCun Y, Denker J, Victorri B. An efficient algorithm for learning invariances in adaptive classifiers. In Conference B: Pattern Recognition Methodology and Systems. Vol. 2. Institute of Electrical and Electronics Engineers Inc. 1992. p. 651-655. 201861 https://doi.org/10.1109/ICPR.1992.201861
Simard, P. ; LeCun, Yann ; Denker, J. ; Victorri, B. / An efficient algorithm for learning invariances in adaptive classifiers. Conference B: Pattern Recognition Methodology and Systems. Vol. 2 Institute of Electrical and Electronics Engineers Inc., 1992. pp. 651-655
@inproceedings{1e274f49d36247f18ac890aa3b8c94fe,
title = "An efficient algorithm for learning invariances in adaptive classifiers",
abstract = "In many machine learning applications, one has not only training data but also some high-level information about certain invariances that the system should exhibit. In character recognition, for example, the answer should be invariant with respect to small spatial distortions in the input images (translations, rotations, scale changes, etcetera). We have implemented a scheme that minimizes the derivative of the classifier outputs with respect to distortion operators of our choosing. This not only produces tremendous speed advantages, but also provides a powerful language for specifying what generalizations we wish the network to perform.",
author = "P. Simard and Yann LeCun and J. Denker and B. Victorri",
year = "1992",
month = "1",
day = "1",
doi = "10.1109/ICPR.1992.201861",
language = "English (US)",
isbn = "0818629150",
volume = "2",
pages = "651--655",
booktitle = "Conference B",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - An efficient algorithm for learning invariances in adaptive classifiers

AU - Simard, P.

AU - LeCun, Yann

AU - Denker, J.

AU - Victorri, B.

PY - 1992/1/1

Y1 - 1992/1/1

N2 - In many machine learning applications, one has not only training data but also some high-level information about certain invariances that the system should exhibit. In character recognition, for example, the answer should be invariant with respect to small spatial distortions in the input images (translations, rotations, scale changes, etcetera). We have implemented a scheme that minimizes the derivative of the classifier outputs with respect to distortion operators of our choosing. This not only produces tremendous speed advantages, but also provides a powerful language for specifying what generalizations we wish the network to perform.

AB - In many machine learning applications, one has not only training data but also some high-level information about certain invariances that the system should exhibit. In character recognition, for example, the answer should be invariant with respect to small spatial distortions in the input images (translations, rotations, scale changes, etcetera). We have implemented a scheme that minimizes the derivative of the classifier outputs with respect to distortion operators of our choosing. This not only produces tremendous speed advantages, but also provides a powerful language for specifying what generalizations we wish the network to perform.

UR - http://www.scopus.com/inward/record.url?scp=77953494628&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77953494628&partnerID=8YFLogxK

U2 - 10.1109/ICPR.1992.201861

DO - 10.1109/ICPR.1992.201861

M3 - Conference contribution

AN - SCOPUS:77953494628

SN - 0818629150

VL - 2

SP - 651

EP - 655

BT - Conference B

PB - Institute of Electrical and Electronics Engineers Inc.

ER -