Indexed by：
Abstract：
This paper is concerned with improving the learning efficiency and stability of neural network. An alternating algorithm is presented for training process. The method is divided into two stages. First, the gradient method is applied. Then the bisection technique is used. The convergence has been proved for the proposed method. So, the stable distribution of weights can be reached. Compared with standard gradient method, the oscillating divergent phenomenon is avoided.
Keyword：
Reprint Author's Address：
Email：
Source ：
Proceedings of 2002 International Conference on Machine Learning and Cybernetics
Year： 2002
Publish Date： 2002-12-01
Volume： 2
Page： 760-762
Language： English
Cited Count：
WoS CC Cited Count： 1
SCOPUS Cited Count：
ESI Highly Cited Papers on the List： 0 Unfold All
WanFang Cited Count：
Chinese Cited Count：
30 Days PV： 2
Affiliated Colleges：
