An improvement for dynamic fuzzy neural network (DFNN) was presented to avoid its running into the local extreme.
针对动态模糊神经网络(DFNN)在进行预测应用时容易陷入“局部极值”的缺陷,提出一种改进方案。
An optimal apportionment of reliability problem of complex system is a nonlinear optimization problem with a large number of local extreme values.
复杂系统可靠度最优分配问题是一个具有多局部极值的非线性的优化问题。
Objective function presents comparatively strong convexity and lesser local extreme values on wide scale which is favour of converging to optimized values.
由于较粗尺度下目标函数呈现较强的凸性及较少的局部极值,很有利于收敛至优化解。
To reduce the computational cost of extreme learning machine (ELM) online training, a new algorithm called local extreme learning machine (LELM) was proposed.
针对训练样本贯序输入时的极端学习机(ELM)训练问题,提出一种可实现在线训练的局域极端学习机(LELM)。
In order to prevent neural network learning from getting into local extreme point, artificial immune network algorithm was used to optimize neural network's parameters.
为了避免神经网络的学习过程陷入局部极值点,采用人工免疫网络优化神经网络的参数。
From experimental results it can be concluded that using a dynamic inertia weight makes the rapidity of convergence accelerate and is not easy to trap in the local extreme points.
函数测试表明,改进后的算法使收敛速度显著加快,而且不易陷入局部极值点。
From experimental results it can be concluded that using a dynamic inertia weight makes the rapidity of convergence accelerate and is not easy to trap in the local extreme points.
函数测试表明,改进后的算法使收敛速度显著加快,而且不易陷入局部极值点。
应用推荐