.png){kind=icon}
Return
Efficient neural network learning using second order information with fuzzy control
.png){kind=icon}
PRE
AI
DOI：10.1016/S0925-2312(01)00336-8.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In this paper, we present a new learning method for back propagation training algorithms for neural networks. With the objective of reducing training time, we first introduce a curved search method with a fixed step size for determining weight adjustments. We then introduce a fuzzy controller for adjusting the step size to further reduce the training time and avoid the spikes in the training curve which sometimes occur with the fixed step size. Computational results indicate a strong potential for significant reduction in training time. (C) 2002 Elsevier Science B.V. All rights reserved.
Keywords:
neural network learning
curved search algorithm
non-linear optimization
fuzzy controller
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W
Organization
No organization information available
Cited Papers
.png){kind=icon}
ShareSaveShareSave
ShareSave no more
no more