Noise tolerance of adaptive resonance theory neural network for binary pattern recognition

Yong Soo Kim; Sunanda Mitra

Noise tolerance of adaptive resonance theory neural network for binary pattern recognition

Yong Soo Kim, Sunanda Mitra

Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Assuming a fast learning condition for an adaptive resonance theory (ART) type neural network, we have explored the effect of the vigilance parameter and the order function on the performance of the neural network for binary pattern recognition. A modified search order was developed for classification of binary alphabet characters and airplane classes and compared with the performance of the original ART-1 network for binary pattern recognition with and without the presence of noise. Our results suggest that the effect of noise on binary pattern recognition is solely dependent on the induced changes in the critical feature patterns when other control parameters remained the same.

Original language	English
Title of host publication	Proceedings of SPIE - The International Society for Optical Engineering
Editors	Simon Haykin
Publisher	Publ by Int Soc for Optical Engineering
Pages	323-330
Number of pages	8
ISBN (Print)	0819406937
State	Published - 1991
Event	Adaptive Signal Processing - San Diego, CA, USA Duration: Jul 22 1991 → Jul 24 1991

Publication series

Name	Proceedings of SPIE - The International Society for Optical Engineering
Volume	1565
ISSN (Print)	0277-786X

Conference

Conference	Adaptive Signal Processing
City	San Diego, CA, USA
Period	07/22/91 → 07/24/91

Access to Document

Link to publication in Scopus

Fingerprint Dive into the research topics of 'Noise tolerance of adaptive resonance theory neural network for binary pattern recognition'. Together they form a unique fingerprint.

Cite this

@inproceedings{dc514cad6633410b9cd259bf26428ad6,

title = "Noise tolerance of adaptive resonance theory neural network for binary pattern recognition",

abstract = "Assuming a fast learning condition for an adaptive resonance theory (ART) type neural network, we have explored the effect of the vigilance parameter and the order function on the performance of the neural network for binary pattern recognition. A modified search order was developed for classification of binary alphabet characters and airplane classes and compared with the performance of the original ART-1 network for binary pattern recognition with and without the presence of noise. Our results suggest that the effect of noise on binary pattern recognition is solely dependent on the induced changes in the critical feature patterns when other control parameters remained the same.",

author = "Kim, {Yong Soo} and Sunanda Mitra",

year = "1991",

language = "English",

isbn = "0819406937",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

publisher = "Publ by Int Soc for Optical Engineering",

pages = "323--330",

editor = "Simon Haykin",

booktitle = "Proceedings of SPIE - The International Society for Optical Engineering",

}

Kim, YS & Mitra, S 1991, Noise tolerance of adaptive resonance theory neural network for binary pattern recognition. in S Haykin (ed.), Proceedings of SPIE - The International Society for Optical Engineering. Proceedings of SPIE - The International Society for Optical Engineering, vol. 1565, Publ by Int Soc for Optical Engineering, pp. 323-330, Adaptive Signal Processing, San Diego, CA, USA, 07/22/91.

Noise tolerance of adaptive resonance theory neural network for binary pattern recognition. / Kim, Yong Soo; Mitra, Sunanda.

Proceedings of SPIE - The International Society for Optical Engineering. ed. / Simon Haykin. Publ by Int Soc for Optical Engineering, 1991. p. 323-330 (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 1565).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Noise tolerance of adaptive resonance theory neural network for binary pattern recognition

AU - Kim, Yong Soo

AU - Mitra, Sunanda

PY - 1991

Y1 - 1991

N2 - Assuming a fast learning condition for an adaptive resonance theory (ART) type neural network, we have explored the effect of the vigilance parameter and the order function on the performance of the neural network for binary pattern recognition. A modified search order was developed for classification of binary alphabet characters and airplane classes and compared with the performance of the original ART-1 network for binary pattern recognition with and without the presence of noise. Our results suggest that the effect of noise on binary pattern recognition is solely dependent on the induced changes in the critical feature patterns when other control parameters remained the same.

AB - Assuming a fast learning condition for an adaptive resonance theory (ART) type neural network, we have explored the effect of the vigilance parameter and the order function on the performance of the neural network for binary pattern recognition. A modified search order was developed for classification of binary alphabet characters and airplane classes and compared with the performance of the original ART-1 network for binary pattern recognition with and without the presence of noise. Our results suggest that the effect of noise on binary pattern recognition is solely dependent on the induced changes in the critical feature patterns when other control parameters remained the same.

UR - http://www.scopus.com/inward/record.url?scp=0026400414&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0026400414

SN - 0819406937

T3 - Proceedings of SPIE - The International Society for Optical Engineering

SP - 323

EP - 330

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

A2 - Haykin, Simon

PB - Publ by Int Soc for Optical Engineering

Y2 - 22 July 1991 through 24 July 1991

ER -