A new approach for testing artificial neural networks

	This Article
	Subscribers, please Login Purchase article: $19 PDF IEEE Xplore Subscribers RSS feed
	Share
	Email this Article to a friend
	Bibliographic References
	ASCII Text BibTex RefWorks Procite/RefMan/Endnote
	Add to:
	Digg Furl Spurl Blink Simpy Google Del.icio.us Y!MyWeb
	Search
	Similar Articles Articles by C.A. Fleischer Articles by L.A. Belfore, II

15th IEEE VLSI Test Symposium (VTS'97)

Monterey, California

April 27-May 01

ISBN: 0-8186-7810-0

	ASCII Text	x
	C.A. Fleischer, L.A. Belfore, II, "A new approach for testing artificial neural networks," VLSI Test Symposium, IEEE, pp. 245, 15th IEEE VLSI Test Symposium (VTS'97), 1997.

	BibTex	x
	@article{ 10.1109/VTEST.1997.600282, author = {C.A. Fleischer and L.A. Belfore, II}, title = {A new approach for testing artificial neural networks}, journal ={VLSI Test Symposium, IEEE}, volume = {0}, year = {1997}, isbn = {0-8186-7810-0}, pages = {245}, doi = {http://doi.ieeecomputersociety.org/10.1109/VTEST.1997.600282}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }

	RefWorks Procite/RefMan/Endnote	x
	TY - CONF JO - VLSI Test Symposium, IEEE TI - A new approach for testing artificial neural networks SN - 0-8186-7810-0 SP EP A1 - C.A. Fleischer, A1 - L.A. Belfore, II, PY - 1997 KW - neural chips; testing; artificial neural networks; interconnection deletion faults; transient behavior; faulted ANN; activation function gains VL - 0 JA - VLSI Test Symposium, IEEE ER -

C.A. Fleischer, Dept. of Electr. & Comput. Eng., Marquette Univ., Milwaukee, WI, USA

L.A. Belfore, II, Dept. of Electr. & Comput. Eng., Marquette Univ., Milwaukee, WI, USA

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/VTEST.1997.600282

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.

Index Terms:

neural chips; testing; artificial neural networks; interconnection deletion faults; transient behavior; faulted ANN; activation function gains

Citation:

C.A. Fleischer, L.A. Belfore, II, "A new approach for testing artificial neural networks," vts, pp.245, 15th IEEE VLSI Test Symposium (VTS'97), 1997

Peer Review Notice | Give Us Feedback

Usage of this product signifies your acceptance of the Terms of Use.