Unsupervised Adaptation to Improve Fault Tolerance of Neural Network Classifiers

E
EH
2004
2004 NASA/DoD Conference on Evolvable Hardware (EH'04)
Abstract - Unsupervised Adaptation to Improve Fault Tolerance of Neural Network Classifiers

	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
	Add to:
	Digg Furl Spurl Blink Simpy Google Del.icio.us Y!MyWeb
	Search
	Similar Articles Articles by Alex Nugent Articles by Garret Kenyon Articles by Reid Porter

2004 NASA/DoD Conference on Evolvable Hardware (EH'04)

Seattle, Washington, USA

June 24-June 26

ISBN: 0-7695-2145-2

	ASCII Text	x
	Alex Nugent, Garret Kenyon, Reid Porter, "Unsupervised Adaptation to Improve Fault Tolerance of Neural Network Classifiers," Evolvable Hardware, NASA/DoD Conference on, pp. 146, 2004 NASA/DoD Conference on Evolvable Hardware (EH'04), 2004.

	BibTex	x
	@article{ 10.1109/EH.2004.1310824, author = {Alex Nugent and Garret Kenyon and Reid Porter}, title = {Unsupervised Adaptation to Improve Fault Tolerance of Neural Network Classifiers}, journal ={Evolvable Hardware, NASA/DoD Conference on}, volume = {0}, year = {2004}, isbn = {0-7695-2145-2}, pages = {146}, doi = {http://doi.ieeecomputersociety.org/10.1109/EH.2004.1310824}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }

	RefWorks Procite/RefMan/Endnote	x
	TY - CONF JO - Evolvable Hardware, NASA/DoD Conference on TI - Unsupervised Adaptation to Improve Fault Tolerance of Neural Network Classifiers SN - 0-7695-2145-2 SP EP A1 - Alex Nugent, A1 - Garret Kenyon, A1 - Reid Porter, PY - 2004 KW - null VL - 0 JA - Evolvable Hardware, NASA/DoD Conference on ER -

Alex Nugent, Space Data Systems Group, Los Alamos, NM

Garret Kenyon, Bio-Physics Group, Los Alamos, NM

Reid Porter, Space Data Systems Group, Los Alamos, NM

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/EH.2004.1310824

We investigate how to exploit the dynamics of unsupervised online learning rules for fault tolerance in neural network classifiers. We first design an adaptation mechanism that keeps neural network weights at a useful fixed point for classification problems. We then demonstrate the robustness of the system when the network inputs are subjected to faults.

Citation:

Alex Nugent, Garret Kenyon, Reid Porter, "Unsupervised Adaptation to Improve Fault Tolerance of Neural Network Classifiers," eh, pp.146, 2004 NASA/DoD Conference on Evolvable Hardware (EH'04), 2004

Peer Review Notice | Give Us Feedback

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