TY - GEN
T1 - A constructive algorithm for feedforward neural networks
AU - Xu, Jinhua
AU - Ho, Daniel W. C.
AU - Zheng, Yufan
PY - 2004
Y1 - 2004
N2 - In this paper, a training and pruning algorithm is proposed for feedforward neural networks based on Jacobian rank deficiency. Redundant nodes will be pruned during the training process, and computational cost of the training algorithm will be reduced significantly. Simulations are presented to demonstrate the effectiveness of the proposed approach.
AB - In this paper, a training and pruning algorithm is proposed for feedforward neural networks based on Jacobian rank deficiency. Redundant nodes will be pruned during the training process, and computational cost of the training algorithm will be reduced significantly. Simulations are presented to demonstrate the effectiveness of the proposed approach.
UR - http://www.scopus.com/inward/record.url?scp=16244418712&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-16244418712&origin=recordpage
M3 - RGC 32 - Refereed conference paper (with host publication)
SN - 0780388739
SN - 9780780388734
VL - 1
SP - 659
EP - 664
BT - 2004 5th Asian Control Conference
T2 - 2004 5th Asian Control Conference
Y2 - 20 July 2004 through 23 July 2004
ER -