TY - JOUR
T1 - Adaptive regularization parameter selection method for enhancing generalization capability of neural networks
AU - Leung, Chi-Tat
AU - Chow, Tommy W.S.
PY - 1999/2
Y1 - 1999/2
N2 - A novel adaptive regularization parameter selection (ARPS) method is proposed in this paper to enhance the performance of the regularization method. The proposed ARPS method enables a gradient descent type training to tunnel through some of the undesired sub-optimal solutions on the composite error surface by means of changing the value of the regularization parameter. Undesired sub-optimal solutions are introduced inherently from regularized objective functions. Hence, the proposed ARPS method is capable of enhancing the regularization method without getting stuck at these sub-optimal solutions.
AB - A novel adaptive regularization parameter selection (ARPS) method is proposed in this paper to enhance the performance of the regularization method. The proposed ARPS method enables a gradient descent type training to tunnel through some of the undesired sub-optimal solutions on the composite error surface by means of changing the value of the regularization parameter. Undesired sub-optimal solutions are introduced inherently from regularized objective functions. Hence, the proposed ARPS method is capable of enhancing the regularization method without getting stuck at these sub-optimal solutions.
UR - http://www.scopus.com/inward/record.url?scp=0033076958&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-0033076958&origin=recordpage
U2 - 10.1016/S0004-3702(98)00115-5
DO - 10.1016/S0004-3702(98)00115-5
M3 - RGC 21 - Publication in refereed journal
SN - 0004-3702
VL - 107
SP - 347
EP - 356
JO - Artificial Intelligence
JF - Artificial Intelligence
IS - 2
ER -