Gradientdescentalgorithm is an efficient method to train FNN, and it can be realized in batch or incremental manner.
梯度下降算法是训练多层前向神经网络的一种有效方法,该算法可以以增量或者批量两种学习方式实现。
2
A few or all of the parameters of the controller are adjusted by using the gradientdescentalgorithm to minimize the output error.
运用最优梯度下降法使目标的计算值与期望值误差最小来迭代优选权重,建立迭代算法模型。
3
Furthermore, the condition of the faster convergence of the proposed algorithm comparing with the conventional gradientdescentalgorithm with momentum term is derived.