Usually, the steepest descent algorithm is used to find the minimum of LOO upper-bound. However, it often gets local optimal solution.
由于该方法易陷入局部最优解，提出了一种基于混合遗传算法求解LOO上界极小点的核参数选择方法。
The one-dimension projection algorithm, which is the steepest descent based, base d on residual space for solving linear equations is analyzed in this paper.
本文分析了基于残差空间求解线性方程组的一维投影算法即最速下降法。
The corresponding adaptive algorithm was derived based on the steepest descent method.
基于最陡下降方法，推导出了相应的自适应算法。
Based on the steepest descent method and the conjugate gradient method, a hybrid algorithm is proposed in this paper, and its global convergence is proved.
将最速下降法与共轭梯度法有机结合起来，构造出一种混合优化算法，并证明其全局收敛性。
The one-dimension projection algorithm, which is the steepest descent method, based on residual space for solving linear equations is analyzed in this paper.
分析了基于残差空间求解线性方程组的一维投影算法、最速下降法和最小剩余法。
The ordinary optimization algorithm can not solve the multi-extreme value problem in data assimilation, so an improvement to steepest descent algorithm is proposed to solve the problem.
对于变分同化中经常遇到的多极值问题，一般的优化算法无法解决。
It is of lower complexity in computation and far more easy to be implemented as compared with the original steepest descent algorithm.
新算法与传统的最陡下降算法相比，具有运算量小、容易实现等优点。
Simulation computations show that it converges faster than the conventional steepest descent backwards error propagation (SDBEP) algorithm.
经模拟计算，它比传统的基于最陡下降方法的误差反传（SDBEP）算法具有更好的收敛性能。
The algorithm which utilizes the Steepest Descent Method can give the estimation of displacement between two frames of image directly.
它对一定时间间隔内两次采样得到的图象进行运算，用最陡梯度下降法直接迭代出图象位移的估计值。
The learning method of hidden-output layer weights is the steepest descent method and the one of input-hidden layer weights is genetic algorithm(GA) .
网络隐层-输出层的权值采取最速下降法学习，输入层-隐层的权值采用遗传算法进行学习；
The learning method of hidden-output layer weights is the steepest descent method and the one of input-hidden layer weights is genetic algorithm(GA) .
网络隐层-输出层的权值采取最速下降法学习，输入层-隐层的权值采用遗传算法进行学习；
应用推荐