In this paper, several artificial neural network based models of solving inverse eigenvalue problem and their characters are studied. These models are direct, indirect and optimization inverse models.
研究了特征值反问题求解的几种神经网络模型：直接逆模型，间接逆模型，优化方法模型，指出了各种方法的应用范围。
In the algorithm, the radial-basis function neural network (RBFNN) is utilized as forward model, and the IGLSA is used to solve the optimization problem in the inverse problem.
该算法中，径向基函数神经网络(RBFNN)用作前向模型，IGLSA用于求解逆问题中的优化问题。
The inverse problem above is actually an optimization problem.
上述问题实质是一个最优化问题。
The solution of inverse problem usually requires nonlinear optimization of an objective function describing the difference between measured and simulated data.
反问题的求解常常需要转化为非线性优化问题，其目标函数定义为观测数据与模型数据之间的残差平方和。
Using this improved arithmetic to solve the inverse problem of EEG, it runs faster and can avoid local optimization more availably than SGA.
为解决电磁场逆问题分析计算过度依赖计算机资源这一“瓶颈”问题，提出了一种新的快速全局优化算法。
Using this improved arithmetic to solve the inverse problem of EEG, it runs faster and can avoid local optimization more availably than SGA.
为解决电磁场逆问题分析计算过度依赖计算机资源这一“瓶颈”问题，提出了一种新的快速全局优化算法。
应用推荐