1) local maximal point and minimal point
局部极点
2) local minimum
局部极小点
1.
The training process of Back Propagation Neural Network (BPNN) is easily converged at a local minimum, which slows the training process sharply.
但在ＢＰ网络的训练过程中 ,如何跳出局部极小点是一个难点 ,对此前人已有一些研究成果 ,其中包括改进的梯度下降搜索法 (ｇｒａｄｉｅｎｔｄｅｓｃｅｎｄｒｅｓｅａｒｃｈ ,ＧＤＲ) [5] 、模拟退火法 (ｓｉｍｕｌａｔｅｄａｎｎｅａｌｉｎｇ ,ＳＡ) [6]和ＥＧＡ算法 (ｅｘｔｅｎｄｅｄｇｅｎｅｔｉｃａｌｇｏｒｉｔｈｍ)等[7,8] 。
2.
The advantages of applying simulated annealing algorithm to short-term load forecast include less model complexity,high forecasting accuracy and global optimal property,which alleviate the tendency of traditional BP algorithm to be trapped in local minimum.
将模拟退火算法应用于短期负荷预测领域,其特点是模型简单、运算效率高,并具有较好的全局最优性能,从而很好地克服了传统BP算法容易陷入局部极小点的缺陷。
3.
Then some defects such as slow convergence rate and getting into local minimum in BP algorithm are pointed out,and the root of the defects is presented.
分析了BP算法的基本原理,指出了BP算法具有收敛速度慢、易陷入局部极小点等缺陷以及这些缺陷产生的根源。
3) local minimum point
局部极小点
1.
A novel global optimization training algorithm was constructed for the feed-forward neural networks to which the BP algorithm is easy to fall into the local minimum point for improper choice of initial weights.
针对前向神经网络BP算法由于初始权值选择不当而陷入局部极小点这一缺陷,提出新的全局优化训练算法。
4) local minimizer
局部极小点
1.
However, due to the existence of multiple local minimiz-ers that differ from the global solution, we have to face two difficulties: how to jump from a local minimizer to a smaller one and how to judge that the current minimizer is a global one.
由于问题本身存在多个不同的局部极小点,在求解过程中面临两个困难:如何跳出当前局部极小点得到函数值更小的局部极小点和如何判断当前的极小点是全局极小点,因此无法直接用传统的非线性规划方法来解决。
5) local minimums
局部极值点
1.
Some particles trapped in local minimums are relocated again by the designed selective behavior based on random mutation and help them break away from local minimums to find the global optimal solution rapidly.
提出了一种改进粒子群优化算法,对标准粒子群优化算法中影响粒子移动方向的4个因子进行了讨论及优化设定,并设计了一种基于随机变异思想的选择操作,在粒子陷入局部极值点时,重新部署粒子,有利于粒子跳出局部极值点,快速搜寻到最优解。
6) escape from the local minima
逃离局部极小点
1.
With the purpose of solving the local minima of standard Back-Propagation(BP) algorithm,a modified error function was proposed to escape from the local minima and converge to the global minima.
对扩展的异或问题正弦函数模拟进行了仿真实验,结果对比表明,改进的BP算法能快速逃离局部极小点,收敛到全局最小点,达到了期望的效果。
补充资料：极点
极点
pole
th Pole)).极点[州e;.0几联] l)坐标的极点是指极坐标(po坛coo川放ltes)的原点. 2)反演(州ersion)的中心也称为极点. 3)直线p关于一条二次曲线(c on‘)的极点是这样一点p，使得直线p是点P关于这条二次曲线的极线(即hr).A.B.地a。撰【补注】关于(解析)函数的极点，见极点(函数的)(po卜(of a ftmction)).有时“极点”一词也用来表示R3中的、中心在原点的单位球上的点(0，0，I)(北极(North卯le)和(O，0，一l)(南极(Sou-
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