总结了正交法的应用研究，提出用正交化方法来确定前馈神经网络的结构，包括隐层数、节点数以及网络训练步数。
Based on summarizing of the application of onhogonal method, an onhogonal method for deciding the number of hidden layers, neurons and the training step of neural networks is presented.
应用隐式时间推进法对不同马赫数的无粘和粘性流动进行数值分析 ，给出了基于预处理方法的高阶精度隐式求解方法。
The Euler solution is obtained using time-marching method by MacCormack two-step finite-difference scheme, which has second-order accuracy in both time and space.
应用推荐