An efficient defect compensation scheme for multi-layer neural networks on WSI devices

Kunihito Yamamori; Toru Abe; Susumu Horiguchi; Ikuo Yoshihara

An efficient defect compensation scheme for multi-layer neural networks on WSI devices

Kunihito Yamamori, Toru Abe, Susumu Horiguchi, Ikuo Yoshihara

Research and Development Divisions

University of Miyazaki

Research output: Contribution to conference › Paper › peer-review

1 Citation (Scopus)

Abstract

This paper discusses on high speed off-line defect compensation scheme for trained multi-layer neural networks implemented in WSI devices. Since partial retraining scheme utilizes the redundancy of neural networks, no additional circuits is needed. The performance of partial retraining scheme will be compared with that by back-propagation algorithm on face image recognition problem.

Original language	English
Pages	1056-1061
Number of pages	6
Publication status	Published - 2002
Event	2002 International Joint Conference on Neural Networks (IJCNN '02) - Honolulu, HI, United States Duration: 2002 May 12 → 2002 May 17

Conference

Conference	2002 International Joint Conference on Neural Networks (IJCNN '02)
Country/Territory	United States
City	Honolulu, HI
Period	02/5/12 → 02/5/17

Cite this

@conference{34836f095c6a4872ae42b09a1de98f51,

title = "An efficient defect compensation scheme for multi-layer neural networks on WSI devices",

abstract = "This paper discusses on high speed off-line defect compensation scheme for trained multi-layer neural networks implemented in WSI devices. Since partial retraining scheme utilizes the redundancy of neural networks, no additional circuits is needed. The performance of partial retraining scheme will be compared with that by back-propagation algorithm on face image recognition problem.",

author = "Kunihito Yamamori and Toru Abe and Susumu Horiguchi and Ikuo Yoshihara",

year = "2002",

language = "English",

pages = "1056--1061",

note = "2002 International Joint Conference on Neural Networks (IJCNN '02) ; Conference date: 12-05-2002 Through 17-05-2002",

}

TY - CONF

T1 - An efficient defect compensation scheme for multi-layer neural networks on WSI devices

AU - Yamamori, Kunihito

AU - Abe, Toru

AU - Horiguchi, Susumu

AU - Yoshihara, Ikuo

PY - 2002

Y1 - 2002

N2 - This paper discusses on high speed off-line defect compensation scheme for trained multi-layer neural networks implemented in WSI devices. Since partial retraining scheme utilizes the redundancy of neural networks, no additional circuits is needed. The performance of partial retraining scheme will be compared with that by back-propagation algorithm on face image recognition problem.

AB - This paper discusses on high speed off-line defect compensation scheme for trained multi-layer neural networks implemented in WSI devices. Since partial retraining scheme utilizes the redundancy of neural networks, no additional circuits is needed. The performance of partial retraining scheme will be compared with that by back-propagation algorithm on face image recognition problem.

UR - http://www.scopus.com/inward/record.url?scp=0036079174&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036079174&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0036079174

SP - 1056

EP - 1061

T2 - 2002 International Joint Conference on Neural Networks (IJCNN '02)

Y2 - 12 May 2002 through 17 May 2002

ER -

An efficient defect compensation scheme for multi-layer neural networks on WSI devices

Abstract

Conference

Other files and links

Fingerprint

Cite this