The first order gradient optimization algorithm is employed to train the network. The training samples stem from the neutron kinetics of the point-reactor.
神经网络的训练采用一阶梯度优化算法，利用点堆中子动力学模型产生训练样本。
The program of DIRECT algorithm that we compiled is universal, it can be used in the first-order, second-order or higher-order PMD compensators, also can be used for other global optimization issues.
文中编写的DIRECT算法程序具有通用性，不仅可以用于一阶、二阶和高阶pmd补偿中，也可用于其它全局最优化问题。
应用推荐