通过一个实例，说明此算法收敛速度较快。
It is shown from an illustrative example that the convergence rate of the algorithm is higher.
BP神经网络已广泛应用于许多领域，但标准BP算法收敛速度很慢。
BP neural network has been widely used in many fields. But the convergent speed of standard BP algorithm is too slow.
仿真结果显示，自然梯度算法比传统梯度算法收敛速度更快，分离效果更好。
Simulation results show that the natural gradient approach has faster convergence speed and better separation performance than the conventional gradient based algorithm.
该算法充分利用了迭代过程中的前几次迭代信息，从而使算法收敛速度更快。
The proposed algorithm has a faster convergence speed, for it USES the information of former iterations.
调整该算法中两个梯度矢量的比例系数，可提高该算法收敛速度、减少收敛后的均方误差。
In the MCMA, adjusting the scale coefficients of two gradient vectors can improve the convergence rate and reduce residual mean square error.
仿真结果验证了算法的有效性，新算法改善了峰值信噪比和恢复效果，提高了算法收敛速度。
Computer simulations show that new algorithm improves peak signal to noise ratio, restoration effects and efficiency of operations, and speeds up the convergence speed.
算法面向实际的运输网络，利用顶点间存在的路径关系，对个体进行优化，从而加速了算法收敛速度。
For a practical transport network, the algorithm used the relations among the points to optimize the individuals. Thus the procedure of the evolution was accelerated.
对合成图像进行仿真，并将表面恢复结果和算法收敛速度与传统的变分迭代方法比较，验证了算法的可行性和实时性。
By recovering surface height of a synthetic image and comparing the result and converging speed with traditional iterative method, the feasibility of the approach is verified.
该算法能够删除掉冗余的连接甚至节点，通过对网络学习步长的动态调整，避免了算法收敛速度过慢和反复震荡的问题。
The algorithm can remove redundant link even nodes on the network, through the network learning step dynamic adjustment to avoid convergence speed of.
而子空间匹配追踪算法可以克服匹配追踪算法中的过匹配现象，加速了算法收敛速度，同时计算量比正交匹配追踪小得多。
SSMP can effectively overcome the over-matching phenomenon in the MP, improves the convergence rate, and has much less computation than the OMP.
针对克隆选择算法收敛速度较慢的问题，对算法策略进行研究，提出了一种基于定向突变的自适应并行免疫算法（APIA）。
Aiming at the slow convergence problem of clonal selection algorithm, this paper proposes an adaptive parallel immune algorithm with orthomutation (APIA).
简要介绍了基于模拟退火思想的粒子群算法的基本原理，并将之应用于盲源分离算法中，以解决基本粒子群算法收敛速度缓慢的问题。
The basic principal of particle swarm optimization based on simulate anneal was introduced and was applied to blind source separation to solve the problem of low searching speed.
本发明与已有的相应技术相比，系统性能可以得到较大的提高，同时本发明中该进的遗传算法相比于传统的遗传算法收敛速度大大加快。
Compared with prior art, the invention improves system performance greatly and the advanced SGA in the invention has faster velocity of convergence, compared with the traditional SGA.
针对复杂区域中流动计算的SIMPLE算法，在选用不同的速度分量作为求解变量和离散体元的界面速度时，进行了算法收敛速度及收敛准确性的对比分析。
With the choices of dependant variables and cell face velocity, the convergency speed and computational accuracy of SIMPLE algorithm employed in the computation of complex flows are analyzed.
本文给出了DISOPE算法收敛速度指标的定义，提出了基于算法与模型参数优选的智能DISOPE方法，有效地改善了DISOPE方法的收敛性能和实用性。
The define of speed index of DISOPE algorithm is given, The intelligent DISOPE method based on optimal selection of algorithm and model parameter.
通过测试函数表明该算法具有较好的收敛速度和稳定性，求解结果非常好。
The test functions show that the algorithm has better convergence speed and stability, the solving result is excellent.
该算法通过增加很少的计算量不仅提高了收敛速度而且获得更小的剩余误差。
This algorithm improves convergence speed and reduces residual error by increasing small the quantity of computation.
最后通过对两个机械优化设计实例进行仿真试验，结果表明本算法求解效率高、收敛速度快、全局搜索能力强。
The simulation test was completed through two mechanical design cases. The result shows that the algorithm has high efficiency, rapid speed of convergence and strong capability of global search.
该文提出了能有效加快收敛速度的修改单纯形算法。
A new modified simplex method can effectively accelerate convergence velocity of iteration.
然后，为了加快遗传算法的收敛速度减少算法执行时间引入模拟退火机制对上述算法进行优化。
Then the mechanism of Simulated Annealing is import in the algorithm above to decrease the execution time and quickens the velocity of convergence.
仿真结果表明，该算法不仅保证了全局收敛性，而且大大提高了算法的收敛速度和稳定性。
The simulation results indicate that this algorithm not only guarantees global convergence, but also improves the converging rate and the stability effectively.
为了对网络参数进行优化，本文提出了一种一般单纯形算法，这种方法比单纯形法收敛速度要快。
In order to optimize the parameters of the network, we propose the General Simplex Method, which converges more quickly than the Simplex Method.
在基本差分进化算法中，融入递增二次函数交叉算子以增加算法的收敛速度。
For the basic differential evolution algorithm, the increasing quadratic function crossover operator was added to increase the convergence speed.
理论分析和大量实验结果表明，本文算法具有收敛速度快和稳定性好。
Theoretical analysis and experimental data show that the new (IES) has high converge speed and stability.
考虑了在一般情况下各种可能的算法模型，分析了这些不同算法的参数选择问题、以及收敛速度问题。
All the possible algorithm models in general conditions have been considered, and parameter choice and convergence speed of these different algorithm were investigated.
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。
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。
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.
应用推荐