Classification of handwritten digits using a RAM neural net architecture

T.M. Jørgensen

doi:10.1142/S0129065797000045

Classification of handwritten digits using a RAM neural net architecture

Research output: Contribution to journal › Conference article › Research › peer-review

Abstract

Results are reported on the task of recognizing handwritten digits without any advanced pre-processing. The result are obtained using a RAM-based neural network, making use of small receptive fields. Furthermore, a technique that introduces negative weights into the RAM net is reported. The results obtained on the task of recognizing handwritten digits is comparable with the best performances reported in the literature.

Original language	English
Journal	International Journal of Neural Systems
Volume	8
Issue number	1
Pages (from-to)	17-25
ISSN	0129-0657
DOIs	https://doi.org/10.1142/S0129065797000045
Publication status	Published - Feb 1997
Event	2nd International Conference on Engineering Applications of Neural Networks - London, United Kingdom Duration: 17 Jun 1996 → 19 Jun 1996 Conference number: 2

Conference

Conference	2nd International Conference on Engineering Applications of Neural Networks
Number	2
Country/Territory	United Kingdom
City	London
Period	17/06/1996 → 19/06/1996

Access to Document

10.1142/S0129065797000045

OpenUrl availability

Full text

Cite this

@inproceedings{feedd23a85fd48a2b62c4e8324dc3568,

title = "Classification of handwritten digits using a RAM neural net architecture",

abstract = "Results are reported on the task of recognizing handwritten digits without any advanced pre-processing. The result are obtained using a RAM-based neural network, making use of small receptive fields. Furthermore, a technique that introduces negative weights into the RAM net is reported. The results obtained on the task of recognizing handwritten digits is comparable with the best performances reported in the literature. ",

keywords = "Optik og sensorsystemer",

author = "T.M. J{\o}rgensen",

year = "1997",

month = feb,

doi = "10.1142/S0129065797000045",

language = "English",

volume = "8",

pages = "17--25",

journal = "International Journal of Neural Systems",

issn = "0129-0657",

publisher = "World Scientific",

number = "1",

note = "2nd International Conference on Engineering Applications of Neural Networks, EANN'96 ; Conference date: 17-06-1996 Through 19-06-1996",

}

TY - GEN

T1 - Classification of handwritten digits using a RAM neural net architecture

AU - Jørgensen, T.M.

N1 - Conference code: 2

PY - 1997/2

Y1 - 1997/2

N2 - Results are reported on the task of recognizing handwritten digits without any advanced pre-processing. The result are obtained using a RAM-based neural network, making use of small receptive fields. Furthermore, a technique that introduces negative weights into the RAM net is reported. The results obtained on the task of recognizing handwritten digits is comparable with the best performances reported in the literature.

AB - Results are reported on the task of recognizing handwritten digits without any advanced pre-processing. The result are obtained using a RAM-based neural network, making use of small receptive fields. Furthermore, a technique that introduces negative weights into the RAM net is reported. The results obtained on the task of recognizing handwritten digits is comparable with the best performances reported in the literature.

KW - Optik og sensorsystemer

U2 - 10.1142/S0129065797000045

DO - 10.1142/S0129065797000045

M3 - Conference article

SN - 0129-0657

VL - 8

SP - 17

EP - 25

JO - International Journal of Neural Systems

JF - International Journal of Neural Systems

IS - 1

T2 - 2nd International Conference on Engineering Applications of Neural Networks

Y2 - 17 June 1996 through 19 June 1996

ER -

Classification of handwritten digits using a RAM neural net architecture

Abstract

Conference

Access to Document

OpenUrl availability

Fingerprint

Cite this