|
| This Article | ||
| ||
| Share | ||
| Bibliographic References | ||
| Add to: | ||
 Digg  Furl  Spurl  Blink  Simpy  Google  Del.icio.us  Y!MyWeb | ||
| Search | ||
| ||
1993 IEEE Virtual Reality Annual International Symposium
A method for training feed forward neural network to be fault tolerant
Seattle, WA, USA
September 18-September 22
ISBN: 0-7803-1363-1
| ASCII Text | x | ||
| H. Elsimary, S. Mashali, S. Shaheen, "A method for training feed forward neural network to be fault tolerant," Virtual Reality Annual International Symposium, pp. 436-441, 1993 IEEE Virtual Reality Annual International Symposium, 1993. | |||
| BibTex | x | ||
| @article{ 10.1109/VRAIS.1993.380747, author = {H. Elsimary and S. Mashali and S. Shaheen}, title = {A method for training feed forward neural network to be fault tolerant}, journal ={Virtual Reality Annual International Symposium}, volume = {0}, year = {1993}, isbn = {0-7803-1363-1}, pages = {436-441}, doi = {http://doi.ieeecomputersociety.org/10.1109/VRAIS.1993.380747}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, } | |||
| RefWorks Procite/RefMan/Endnote | x | ||
| TY - CONF JO - Virtual Reality Annual International Symposium TI - A method for training feed forward neural network to be fault tolerant SN - 0-7803-1363-1 SP436 EP441 A1 - H. Elsimary, A1 - S. Mashali, A1 - S. Shaheen, PY - 1993 KW - interconnection weight KW - network output deviation KW - error representation KW - training KW - feedforward neural network KW - weight perturbations KW - fault tolerance VL - 0 JA - Virtual Reality Annual International Symposium ER - | |||
A method for training a feedforward neural network to be fault tolerant against weight perturbations is described. The measure for fault tolerance is the deviation of the network's output after training, when each interconnection weight is perturbed, from that output without perturbation. In this method, an attempt is made to keep that deviation as low as possible. This measure is used because it can represent that kinds of error which arises when neural networks are implemented in hardware.
Index Terms:
interconnection weight, network output deviation, error representation, training, feedforward neural network, weight perturbations, fault tolerance
Citation:
H. Elsimary, S. Mashali, S. Shaheen, "A method for training feed forward neural network to be fault tolerant," vrais, pp.436-441, 1993 IEEE Virtual Reality Annual International Symposium, 1993
Usage of this product signifies your acceptance of the Terms of Use.