1) Powell optimization algorithm
Powell寻优算法
1.
In this paper, CT/PET multimodality medical image registration is performed by a region similarity measure(RSM), accompanied with an improved segment method and Powell optimization algorithm.
结合Powell寻优算法实现了CT/PET多模医学图像配准。
2) Powell's optimizing method
Powell最优化算法
3) Powell optimal method
Powell优化法
4) Optimization Algorithm
寻优算法
1.
This paper presented a novel optimization algorithm based on simulating the behavior and habit of fisher\' fishing.
实例测试结果表明,该算法具有较好的搜索性能,因而该寻优算法是有效的和可行的。
5) Powell algorithm
Powell算法
1.
To train the weights of NN,it proposed a new hybrid algorithm consisting of Powell algorithm and simulated annealing algorithm with adaptive cooling schedule.
为解决非线性系统辨识和预测问题,以多层前向网络为模型框架,采用带自适应冷却进度表的模拟退火算法与Powell算法构成新型混合算法,训练网络的权值。
2.
The algorithm consists of Powell algorithm and simulated annealing algorithm with adaptive cooling schedule.
针对训练神经网络权值的BP算法容易陷于局部最小值点的问题,提出了带自适应冷却进度表的模拟退火算法与Powell算法构成新型混合算法,用该算法训练网络的权值。
3.
The non-linear least square formula for the difference of reference and sensed images is seen as the object function for Powell algorithm in which motion parameters are used as variations.
用参考图像和待配准图像构造的非线性最小二乘公式作为Powell算法的目标函数,并且以运动参数作为变量。
6) Powell search algorithm
Powell算法
1.
With modified mutual information(MI) measure,Powell search algorithm is utilized to realize mono-modality image registration.
主要改进了互信息和归一化互信息的公式,减小了互信息的计算量;改进了Powell算法,保持了原搜索方向并有效避免了局部极值;用预设旋转量的方法解决了同模态医学图像配准的局部极值问题,同时,还讨论了Powell收敛阈值对配准速度的影响。
2.
A novel algorithm that combines the global search ability of PSO algorithm and the local best result of Powell search algorithm is proposed where,after each time iterated algorithm of PSO,a Powell algorithm is used to get the best result of the current local result.
提出了一种基于粒子群算法PSO和Powell的混合优化算法,将PSO算法的全局搜索能力与Powell算法的局部寻优能力有机地结合起来。
补充资料:Powell’s method Powell
分子式:
CAS号:
性质:法是在无约束优化算法之一,首先选取一组共轭方向,从某个初始点出发,求目标函数在这些方向上的极小值点,然后以该点为新的出发点,重复这一过程直到获得满意解,其优点是不必计算目标函数的梯度就可以在有限步内找到极值点。
CAS号:
性质:法是在无约束优化算法之一,首先选取一组共轭方向,从某个初始点出发,求目标函数在这些方向上的极小值点,然后以该点为新的出发点,重复这一过程直到获得满意解,其优点是不必计算目标函数的梯度就可以在有限步内找到极值点。
说明:补充资料仅用于学习参考,请勿用于其它任何用途。
参考词条