Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
Neural networks and fuzzy control with applications to textile manufacturing and management
Neural networks and fuzzy control with applications to textile manufacturing and management
| Hi-index | 0.00 |
In this paper, we develop a curved search algorithm which uses second-order information, for the learning algorithm for a supervised neural network. With the objective of reducing the training time, we introduce a fuzzy controller for adjusting the first and second-order approximation parameters in the iterative method to further reduce the training time and to avoid the spikes in the learning curve which sometimes occurred with the fixed step length. Computational results indicate a significant reduction in training when comparing with the delta learning rule.