TY - JOUR
T1 - Prediction error of a fault tolerant neural network
AU - Sum, John
AU - Leung, Andrew Chi-Sing
PY - 2008/12
Y1 - 2008/12
N2 - Prediction error is a powerful tool that measures the performance of a neural network. In this paper, we extend the technique to a kind of fault tolerant neural networks. Considering a neural network with multiple-node fault, we derive its generalized prediction error. Hence, the effective number of parameters of such a fault tolerant neural network is obtained. The difficulty in obtaining the mean prediction error is discussed. Finally, a simple procedure for estimation of the prediction error is empirically suggested.
AB - Prediction error is a powerful tool that measures the performance of a neural network. In this paper, we extend the technique to a kind of fault tolerant neural networks. Considering a neural network with multiple-node fault, we derive its generalized prediction error. Hence, the effective number of parameters of such a fault tolerant neural network is obtained. The difficulty in obtaining the mean prediction error is discussed. Finally, a simple procedure for estimation of the prediction error is empirically suggested.
KW - Fault tolerant neural networks
KW - Prediction error
KW - RBF network
UR - http://www.scopus.com/inward/record.url?scp=56149099331&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-56149099331&origin=recordpage
U2 - 10.1016/j.neucom.2008.05.009
DO - 10.1016/j.neucom.2008.05.009
M3 - RGC 21 - Publication in refereed journal
SN - 0925-2312
VL - 72
SP - 653
EP - 658
JO - Neurocomputing
JF - Neurocomputing
IS - 1-3
ER -