Dynaic learning rate neural network training and composite structural damage detection

摘要

A new learning procedure, called dynamic learning rte steepest descent (DSD) method, is proposed for training neural networks. Based on the simple steepest descendent method, the proposed method improves the learning convergence speed significantly without increasing the computational effort, the memory cost, the algorithm sim- plicity, and the computational locality in the standary layered error backpropagating training algorithm.