메뉴 건너뛰기




Volumn 2002-January, Issue , 2002, Pages 293-300

Comparison of defect compensation methods for feedforward neural networks

Author keywords

Fault tolerance; Feedforward neural networks; Feedforward systems; Image recognition; Information science; Large scale integration; Neural network hardware; Neural networks; Neurons; Robustness

Indexed keywords

ALGORITHMS; BACKPROPAGATION ALGORITHMS; DEFECTS; FAULT TOLERANCE; HARDWARE; IMAGE RECOGNITION; INFORMATION SCIENCE; LSI CIRCUITS; NEURAL NETWORKS; NEURONS; ROBUSTNESS (CONTROL SYSTEMS); WORLD WIDE WEB;

EID: 84948773205     PISSN: 15410110     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/PRDC.2002.1185649     Document Type: Conference Paper
Times cited : (1)

References (7)
  • 1
    • 0000654595 scopus 로고    scopus 로고
    • Improvement of MTTF of Feedforward Neural networks by Retraining
    • in Japanese
    • Y. Tohma and M. Abe. Improvement of MTTF of Feedforward Neural networks by Retraining, IEICE, vol. J 81-D-1, no. 1, pp.1379-1386, 1999(in Japanese)
    • (1999) IEICE , vol.J 81-D-1 , Issue.1 , pp. 1379-1386
    • Tohma, Y.1    Abe, M.2
  • 5
    • 84948751314 scopus 로고    scopus 로고
    • Performance evalution of a partial retraining scheme for defective multi-layer neural networks
    • K. Yamamori, T. Abe, and S. Horiguchi. Performance Evalution of a Partial Retraining Scheme for Defective Multi-Layer Neural Networks, Australian Computer Science Communications, volume 23, Number 4, pp138-145, 2001
    • (2001) Australian Computer Science Communications , vol.23 , Issue.4 , pp. 138-145
    • Yamamori, K.1    Abe, T.2    Horiguchi, S.3


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.