Neural network transformation of arbitrary Boolean functions

Basit Hussain, Mansur R. Kabuka

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

7 Citations (Scopus)

Abstract

Boolean logic is considered to be a good source for classification problems, an area dominated by neural networks. Although quite a few algorithms exist for training and implementing neural networks, no technique exists that can guarantee the transformation of any arbitrary Boolean function to neural networks. This paper describes a method that accomplishes exactly that. The algorithm is tested on the classic character recognition problem using translated, rotated, deformed, and noisy patterns. The initial simulation results are presented. Comparison of the proposed network to several popular existing networks has been performed and its advantages outlined. The future direction of research has also been explained.

Original languageEnglish
Title of host publicationProceedings of SPIE - The International Society for Optical Engineering
Place of PublicationBellingham, WA, United States
PublisherPubl by Int Soc for Optical Engineering
Pages355-367
Number of pages13
Volume1766
ISBN (Print)0819409391
StatePublished - Dec 1 1992
EventNeural and Stochastic Methods in Image and Signal Processing - San Diego, CA, USA
Duration: Jul 20 1992Jul 23 1992

Other

OtherNeural and Stochastic Methods in Image and Signal Processing
CitySan Diego, CA, USA
Period7/20/927/23/92

Fingerprint

Boolean functions
Neural networks
Character recognition
character recognition
logic
education
simulation

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Condensed Matter Physics

Cite this

Hussain, B., & Kabuka, M. R. (1992). Neural network transformation of arbitrary Boolean functions. In Proceedings of SPIE - The International Society for Optical Engineering (Vol. 1766, pp. 355-367). Bellingham, WA, United States: Publ by Int Soc for Optical Engineering.

Neural network transformation of arbitrary Boolean functions. / Hussain, Basit; Kabuka, Mansur R.

Proceedings of SPIE - The International Society for Optical Engineering. Vol. 1766 Bellingham, WA, United States : Publ by Int Soc for Optical Engineering, 1992. p. 355-367.

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

Hussain, B & Kabuka, MR 1992, Neural network transformation of arbitrary Boolean functions. in Proceedings of SPIE - The International Society for Optical Engineering. vol. 1766, Publ by Int Soc for Optical Engineering, Bellingham, WA, United States, pp. 355-367, Neural and Stochastic Methods in Image and Signal Processing, San Diego, CA, USA, 7/20/92.
Hussain B, Kabuka MR. Neural network transformation of arbitrary Boolean functions. In Proceedings of SPIE - The International Society for Optical Engineering. Vol. 1766. Bellingham, WA, United States: Publ by Int Soc for Optical Engineering. 1992. p. 355-367
Hussain, Basit ; Kabuka, Mansur R. / Neural network transformation of arbitrary Boolean functions. Proceedings of SPIE - The International Society for Optical Engineering. Vol. 1766 Bellingham, WA, United States : Publ by Int Soc for Optical Engineering, 1992. pp. 355-367
@inproceedings{2ee3351fe3c94d8e936c168033d36a32,
title = "Neural network transformation of arbitrary Boolean functions",
abstract = "Boolean logic is considered to be a good source for classification problems, an area dominated by neural networks. Although quite a few algorithms exist for training and implementing neural networks, no technique exists that can guarantee the transformation of any arbitrary Boolean function to neural networks. This paper describes a method that accomplishes exactly that. The algorithm is tested on the classic character recognition problem using translated, rotated, deformed, and noisy patterns. The initial simulation results are presented. Comparison of the proposed network to several popular existing networks has been performed and its advantages outlined. The future direction of research has also been explained.",
author = "Basit Hussain and Kabuka, {Mansur R.}",
year = "1992",
month = "12",
day = "1",
language = "English",
isbn = "0819409391",
volume = "1766",
pages = "355--367",
booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "Publ by Int Soc for Optical Engineering",

}

TY - GEN

T1 - Neural network transformation of arbitrary Boolean functions

AU - Hussain, Basit

AU - Kabuka, Mansur R.

PY - 1992/12/1

Y1 - 1992/12/1

N2 - Boolean logic is considered to be a good source for classification problems, an area dominated by neural networks. Although quite a few algorithms exist for training and implementing neural networks, no technique exists that can guarantee the transformation of any arbitrary Boolean function to neural networks. This paper describes a method that accomplishes exactly that. The algorithm is tested on the classic character recognition problem using translated, rotated, deformed, and noisy patterns. The initial simulation results are presented. Comparison of the proposed network to several popular existing networks has been performed and its advantages outlined. The future direction of research has also been explained.

AB - Boolean logic is considered to be a good source for classification problems, an area dominated by neural networks. Although quite a few algorithms exist for training and implementing neural networks, no technique exists that can guarantee the transformation of any arbitrary Boolean function to neural networks. This paper describes a method that accomplishes exactly that. The algorithm is tested on the classic character recognition problem using translated, rotated, deformed, and noisy patterns. The initial simulation results are presented. Comparison of the proposed network to several popular existing networks has been performed and its advantages outlined. The future direction of research has also been explained.

UR - http://www.scopus.com/inward/record.url?scp=0026973225&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026973225&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0819409391

VL - 1766

SP - 355

EP - 367

BT - Proceedings of SPIE - The International Society for Optical Engineering

PB - Publ by Int Soc for Optical Engineering

CY - Bellingham, WA, United States

ER -