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

Kunihito Yamamori, Toru Abe, Susumu Horiguchi, Ikuo Yoshihara

Research output: Contribution to conferencePaperpeer-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 languageEnglish
Pages1056-1061
Number of pages6
Publication statusPublished - 2002 Jan 1
Externally publishedYes
Event2002 International Joint Conference on Neural Networks (IJCNN '02) - Honolulu, HI, United States
Duration: 2002 May 122002 May 17

Other

Other2002 International Joint Conference on Neural Networks (IJCNN '02)
CountryUnited States
CityHonolulu, HI
Period02/5/1202/5/17

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'An efficient defect compensation scheme for multi-layer neural networks on WSI devices'. Together they form a unique fingerprint.

Cite this