This paper has offered a kind of feasible experiment method and meaningful results to optimum design and manufacturing of functional gradient material.
从而为优化设计和制备梯度功能材料提供了一种可行的实验方法和有意义的结果。
BP neural network, as its nature of gradient descent method, is easy to fall into local optimum.
但BP神经网络本质是梯度下降法，容易陷入局部最优。
In the iterative procedure, adopt the gradient step method and the optimum vector method to calculate.
迭代过程中，采用梯度步和最佳矢量步进行计算。
应用推荐