然后利用梯度下降法推导了基于最优模式中心的NLDA算法。
The second algorithm calculates the optimum classes' centres of NLDA by method of grads descending.
首先研究了离线训练的滑模控制器，然后，给出了利用梯度下降法的在线训练方法。
First, a study of a sliding mode controller under on off training is made and then the on line learning algorithm using a gradient decent method is designed.
利用梯度下降法对网络的权值进行训练，并且推导了BVS的增长算法，以及网络训练的限制记忆递推公式。
The weights are trained with Gradient Descent Method. The increase algorithm of BVS, and restricted algorithm, was induced.
对于参数的学习，提出了一种适用于分类器的可微经验风险函数，该函数能够有效地利用梯度下降法进行最小化。
For the learning process, a new kind of empirical risk function is proposed which is differentiable and can be minimized by gradient descent strategy.
通过对泛函网络的分析，提出了一种序列泛函网络模型及学习算法，而网络的泛函参数利用梯度下降法来进行学习。
In this paper, by analyzing the functional network, a new model and learning algorithm of the serial functional networks is proposed.
通过对泛函网络的分析，提出了一种序列泛函网络模型及学习算法，而网络的泛函参数利用梯度下降法来进行学习。
In this paper, by analyzing the functional network, a new model and learning algorithm of the serial functional networks is proposed.
应用推荐