Handwritten Digit Recognition: A Neural Network Demo

Berend-Jan van der Zwaag

doi:10.1007/3-540-45493-4_75

Handwritten Digit Recognition: A Neural Network Demo

Universiteit Twente

Research output: Chapter in Book/Report/Conference proceeding › Contribution to conference proceeding › Academic › peer-review

Abstract

A handwritten digit recognition system was used in a demonstration project to visualize artificial neural networks, in particular Kohonen's self-organizing feature map. The purpose of this project was to introduce neural networks through a relatively easy-to-understand application to the general public. This paper describes several techniques used for preprocessing the handwritten digits, as well as a number of ways in which neural networks were used for the recognition task. Whereas the main goal was a purely educational one, a moderate recognition rate of 98% was reached on a test set. © Springer-Verlag 2001.

Original language	English
Title of host publication	International Conference on Computational Intelligence
Subtitle of host publication	Fuzzy Days
Publisher	Springer Nature
Pages	762-771
Number of pages	10
ISBN (Electronic)	978-3-540-45493-9
ISBN (Print)	978-3-540-42732-2
DOIs	https://doi.org/10.1007/3-540-45493-4_75
Publication status	Published - 1 Jan 2001
Externally published	Yes
Event	Computational Intelligence. Theory and Applications: 7th Fuzzy Days Dortmund - Dortmund, Germany Duration: 1 Oct 2001 → 3 Oct 2001

Conference

Conference	Computational Intelligence. Theory and Applications
Country/Territory	Germany
City	Dortmund
Period	1/10/01 → 3/10/01

Keywords

neural networks
computational intelligence

Access to Document

10.1007/3-540-45493-4_75

Cite this

@inproceedings{b148d6f7801f48bd9e3a2a78b0a0ca30,

title = "Handwritten Digit Recognition: A Neural Network Demo",

abstract = "A handwritten digit recognition system was used in a demonstration project to visualize artificial neural networks, in particular Kohonen's self-organizing feature map. The purpose of this project was to introduce neural networks through a relatively easy-to-understand application to the general public. This paper describes several techniques used for preprocessing the handwritten digits, as well as a number of ways in which neural networks were used for the recognition task. Whereas the main goal was a purely educational one, a moderate recognition rate of 98% was reached on a test set. {\textcopyright} Springer-Verlag 2001.",

keywords = "neural networks, computational intelligence, neurale netwerken, computationele intelligentie",

author = "Zwaag, {Berend-Jan van der}",

note = "DBLP License: DBLP's bibliographic metadata records provided through http://dblp.org/ are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.; Computational Intelligence. Theory and Applications : 7th Fuzzy Days Dortmund ; Conference date: 01-10-2001 Through 03-10-2001",

year = "2001",

month = jan,

day = "1",

doi = "10.1007/3-540-45493-4_75",

language = "English",

isbn = "978-3-540-42732-2",

pages = "762--771",

booktitle = "International Conference on Computational Intelligence",

publisher = "Springer Nature",

address = "United Kingdom",

}

TY - GEN

T1 - Handwritten Digit Recognition

T2 - Computational Intelligence. Theory and Applications

AU - Zwaag, Berend-Jan van der

N1 - DBLP License: DBLP's bibliographic metadata records provided through http://dblp.org/ are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.

PY - 2001/1/1

Y1 - 2001/1/1

N2 - A handwritten digit recognition system was used in a demonstration project to visualize artificial neural networks, in particular Kohonen's self-organizing feature map. The purpose of this project was to introduce neural networks through a relatively easy-to-understand application to the general public. This paper describes several techniques used for preprocessing the handwritten digits, as well as a number of ways in which neural networks were used for the recognition task. Whereas the main goal was a purely educational one, a moderate recognition rate of 98% was reached on a test set. © Springer-Verlag 2001.

AB - A handwritten digit recognition system was used in a demonstration project to visualize artificial neural networks, in particular Kohonen's self-organizing feature map. The purpose of this project was to introduce neural networks through a relatively easy-to-understand application to the general public. This paper describes several techniques used for preprocessing the handwritten digits, as well as a number of ways in which neural networks were used for the recognition task. Whereas the main goal was a purely educational one, a moderate recognition rate of 98% was reached on a test set. © Springer-Verlag 2001.

KW - neural networks

KW - computational intelligence

KW - neurale netwerken

KW - computationele intelligentie

U2 - 10.1007/3-540-45493-4_75

DO - 10.1007/3-540-45493-4_75

M3 - Contribution to conference proceeding

SN - 978-3-540-42732-2

SP - 762

EP - 771

BT - International Conference on Computational Intelligence

PB - Springer Nature

Y2 - 1 October 2001 through 3 October 2001

ER -

Handwritten Digit Recognition: A Neural Network Demo

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this