Title :
A new approach for testing artificial neural networks
Author :
Fleischer, Curtis A. ; Belfore, Lee A., II
Author_Institution :
Dept. of Electr. & Comput. Eng., Marquette Univ., Milwaukee, WI, USA
fDate :
27 Apr-1 May 1997
Abstract :
This paper presents progress on a new and novel testing approach for detecting interconnection deletion faults in electronic implementations of artificial neural networks (ANNs). The testing approach is based on an unusual transient behavior manifested by faulted ANNs showing better apparent performance than fault-free ANNs, when neurons are operated with low activation function gains. The result presented in this paper improves on prior results by requiring fewer test patterns
Keywords :
VLSI; automatic testing; built-in self test; integrated circuit testing; neural chips; activation function gains; artificial neural networks; faulted ANN; interconnection deletion faults; testing; transient behavior; Artificial neural networks; Automatic testing; Circuit faults; Circuit simulation; Circuit testing; Electrical fault detection; Electronic equipment testing; Integrated circuit interconnections; Manufacturing; Neurons;
Conference_Titel :
VLSI Test Symposium, 1997., 15th IEEE
Conference_Location :
Monterey, CA
Print_ISBN :
0-8186-7810-0
DOI :
10.1109/VTEST.1997.600282
