您要查找的是不是：
- solving slow convergence problem 解决慢收敛问题
- slow convergence problem 慢收敛问题
- The extension of reinforcement learning to MDPs with large state,action space and high complexity has inevitably encountered the problem of the curse of dimensionality,which results in slow convergence and long training time. 传统的强化学习算法应用到大状态、动作空间和任务复杂的马尔可夫决策过程问题时;存在收敛速度慢;训练时间长等问题.
- Thus, both slow convergence and randomicity in the time-interval between samples on the genetic algorithm are overcome. 克服了遗传算法收敛慢和每个采样周期输出的随机性。
- The algorithm overcomes the drawbacks of conventional BP training such as slow convergence and the tendency to be entrapped in local minimum. 该法克服了传统BP算法因用梯度下降和误差逆向传播而拖慢收敛速度及易陷于局部极小的缺点。
- To solve the premature convergence problem of the Particle Swarm Optimization (PSO), an improved PSO method was proposed. 针对粒子群优化算法早熟收敛现象，提出了一种改进的粒子群优化算法。
- As for the slow convergence rate of BP algorithm, a momentum item was introduced into BP algorithm so that the convergence rate was increased. 针对BP神经网络收敛慢的特点,在实际算法中引入了动量项,从而提高了网络收敛速度。
- Q-learning is a typical RL method with a slow convergence speed especially as the scales of the state space and the action space increase. 利用模糊综合决策方法处理专家经验和环境信息得到Q学习的先验知识，对Q学习的初始状态进行优化。
- In order to solve the premature convergence problem of particle swarm optimization，a novel fuzzy adaptive Particle Swarm Optimization based on T-S model（T-SPSO） is presented. 摘要 针对微粒群优化算法存在的早熟问题，提出了一种基于T-S模型的模糊自适应PSO算法（T-SPSO算法）。
- GA is a randomoptimization algorithm with global optimum capability, but it has the disadvantages of slow convergence and precocity. 遗传算法是一种具有全局寻优能力的随机搜索算法，但其本身存在收敛速度慢和易早熟的缺陷。
- The model overcomes some flaws of popular learning algorithm such as local minima, slow convergence and initialized values. 该模型克服了传统入侵检测系统所存在的局部极小、收敛速度慢、初值敏感性等问题。
- To overcome the default of slow convergence speed，precocity and stagnation in the basic ant colony Algorithm（ACA），we proposed an Efficient Ant Colony Algorithm（EACA）. 摘要 为了克服基本蚁群算法求解速度慢、易于出现早熟和停滞现象的缺陷，提出了一种高效的蚁群算法（EACA）。
- However, the training of NNs by conventional back-propagation (BP), i. e. the BP-NNs, has intrinsic vulnerable weakness in slow convergence and local minina. 常规的神经网络权值训练算法，例如误差反传算法，存在着收敛速度慢，容易陷入局部极值点等问题。
- An improved PSO (particle swarm optimization) algorithm is presented which well addresses slow convergence speed and low calculation precision in the basic PSO algorithm. 摘要提出了一种改进的粒子群算法，很好地解决了基本粒子群算法中易陷入局部最优的缺点。
- An offset surface method was proposed to calculate the discrete mandril's height, whose algorithm was very simple and without the convergence problem which is common to analytical algorithm. 提出了采用偏移球心曲面计算顶杆高度的方法，算法实现简单，无解析算法产生的收敛问题。
- 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。
- Proposes an improved inertia weight mutation particle swarm optimization to solve the premature convergence problem,and to avoid the slowconvergence in the later convergence phase. 针对微粒群优化算法的早熟收敛和进化后期收敛速度慢等问题,提出了一种改进惯性权重的变异微粒群优化算法。
- Considering the premature convergence problem in the conventional differential evolution algorithm，a density clustering based niching Differential Evolution algorithm is proposed in this paper. 摘要 针对基本差分进化算法早熟收敛的缺陷，提出了一种基于密度聚类的小生境差分进化算法。
- The experimental results demonstrate that the proposed approach surmounts effectively the local convergence problem of standard genetic algorithm and improves the test generation speed. 实验结果表明，所提出的方法能有效克服标准遗传算法中的局部收敛问题，加快了测试生成过程。
- But BP network has many intrinsic defects, the structure is difficult to confirm,the blindness that initial weights is chosen results in slow convergence speed andeasily falling into local minimum. 但 bp 网络有很多固有缺陷,结构难确定,初始权值选择的盲目性导致训练速度慢,容易陷入局部最小。
