𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Optimally generalizing neural networks with the ability to recover from single stuck-at r faults

✍ Scribed by Hidekazu Iwaki; Hidemitsu Ogawa; Akira Hirabayashi


Publisher
John Wiley and Sons
Year
2002
Tongue
English
Weight
246 KB
Volume
33
Category
Article
ISSN
0882-1666

No coin nor oath required. For personal study only.

✦ Synopsis


Abstract

Handling faults is an important issue for hardware implementation of hierarchical neural networks. This paper presents a method for complete recovery of prefault input/output relations by modifying only the normal connection weights when a fault or a stuck‐at r fault occurs. We derive the necessary and sufficient conditions for which the number of intermediate elements and the intermediate element function are satisfied, in order to restore complete prefault functionality. We then develop a concrete method for creating an intermediate element function which satisfies these conditions and a method for modifying the connection weights when a fault occurs. © 2002 Wiley Periodicals, Inc. Syst Comp Jpn, 33(7): 114–123, 2002; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.1147