Description: 本算法在训练步数、训练时间及其误差精度等方面都优于常规的模糊神经网络，其学习收敛速度快、误差曲线也更稳定。-the algorithm steps in training, training time and error accuracy is superior to the conventional fuzzy neural network, learning fast convergence, the error curve is more stable. Platform: |
Size: 1641 |
Author:王鹏 |
Hits:
Description: 这是一个pso程序源代码，pso源于对鸟群捕食行为的研究而发明的进化计算技术，属于进化算法的一种。
优点：收敛速度快，具有全局寻优能力，而且编程简单，易于推广使用。 -This is a pso source code, pso out of the flock of predatory behavior and evolutionary computation invention of the technology is an evolutionary algorithm. Advantages : fast convergence with global optimization capability and programming simple and easy to use. Platform: |
Size: 12470 |
Author:张清 |
Hits:
Description: Because of the poor observability of Inertial Navigation System on stationary base, the estimation
error of the azimuth will converge very slowly in initial alignment by means of Kalmari filtering, and making the
time initial alignment is longer. In this paper, a fast estimation method of the azimuth error is creatively proposed
for the initial alignment of INS on stationary base. On the basis of the the fast convergence of the leveling error,
the azimuth error can be directly calculated. By means of this fast initial alignment method, the time of initial
alignment is reduced greatly. The computer simulation results illustrate the efficiency of the method. Platform: |
Size: 188171 |
Author:huzhou |
Hits:
Description: 解非线性方程组的一种方法：先用一种优化方法将给定初值（它有可能会使得后续的牛顿法发散）通过一条比较快的途径收敛到精确解附近，得到一个新的初始点，然后再通过牛顿法将新的初始点迭代到精确解（一定的误差范围内）。这种方法的优点在于：它可以将牛顿法快速收敛的优势发挥出来，同时又避免了该方法收敛域比较窄的缺点。-solving nonlinear equations in a way : by using a method of optimizing initial Givens (it might make follow-up to Newton's law divergence) adopted a relatively fast convergence to the channel near the exact solution, to be a new starting point, and then Newton's law of the new iteration of the initial point of the exact solution ( some of error). This method has the advantage : it can be rapid convergence of Newton's method to exploit the advantages while avoiding convergence of the method is relatively narrow domain shortcomings. Platform: |
Size: 33395 |
Author:王廷 |
Hits:
Description: 解非线性方程组的一种方法：先用一种优化方法将给定初值（它有可能会使得后续的牛顿法发散）通过一条比较快的途径收敛到精确解附近，得到一个新的初始点，然后再通过牛顿法将新的初始点迭代到精确解（一定的误差范围内）。这种方法的优点在于：它可以将牛顿法快速收敛的优势发挥出来，同时又避免了该方法收敛域比较窄的缺点。-solving nonlinear equations in a way : by using a method of optimizing initial Givens (it might make follow-up to Newton's law divergence) adopted a relatively fast convergence to the channel near the exact solution, to be a new starting point, and then Newton's law of the new iteration of the initial point of the exact solution ( some of error). This method has the advantage : it can be rapid convergence of Newton's method to exploit the advantages while avoiding convergence of the method is relatively narrow domain shortcomings. Platform: |
Size: 32768 |
Author:王廷 |
Hits:
Description: 本算法在训练步数、训练时间及其误差精度等方面都优于常规的模糊神经网络，其学习收敛速度快、误差曲线也更稳定。-the algorithm steps in training, training time and error accuracy is superior to the conventional fuzzy neural network, learning fast convergence, the error curve is more stable. Platform: |
Size: 1024 |
Author:王鹏 |
Hits:
Description: 这是一个pso程序源代码，pso源于对鸟群捕食行为的研究而发明的进化计算技术，属于进化算法的一种。
优点：收敛速度快，具有全局寻优能力，而且编程简单，易于推广使用。 -This is a pso source code, pso out of the flock of predatory behavior and evolutionary computation invention of the technology is an evolutionary algorithm. Advantages : fast convergence with global optimization capability and programming simple and easy to use. Platform: |
Size: 12288 |
Author:张清 |
Hits:
Description: 本文在量子进化算法的基础上结合基于克隆选择学说的克隆算子,提出了改进的进化算法———量子克
隆进化策略算法(QCES) . 它既借鉴了量子进化算法的高效并行性又利用克隆算子来代替其中的变异和选择操作,以
增加种群的多样性,避免了早熟,且收敛速度快. 本文不仅从理论上证明了该算法的收敛,而且通过仿真实验表明了此
算法的优越性.-In this paper, quantum evolutionary algorithm based on the combination of clonal selection theory based on the cloning operator, made an improved evolutionary algorithm--- quantum cloning evolutionary strategy algorithm (QCES). It draws on quantum evolutionary algorithm and also makes use of parallelism and efficient cloning operator to replace one of the variation and selection of operation in order to increase population diversity to avoid premature, and fast convergence. This article is not only theoretically proved that the convergence of the algorithm, and through simulation experiments show the superiority of this algorithm . Platform: |
Size: 197632 |
Author: |
Hits:
Description: 本代码是关于医学图像的边缘检测，可实现快速的的收敛到感兴趣边缘，matlab编程。-The code is on the medical image edge detection, can be achieved fast convergence to the edge of interest, matlab programming. Platform: |
Size: 9216 |
Author:hujin |
Hits:
Description: 微粒子群算法的C实现，实现的是基本微粒群算法，微粒群算法是一种基于群智能方法的演化计算技术，本算法实现容易，收敛速度快-Microparticle Swarm C realize, realize that the basic particle swarm optimization, particle swarm optimization is a group of intelligent methods based on the evolution of computing technology, easy to realize this algorithm, fast convergence Platform: |
Size: 6144 |
Author:小淘 |
Hits:
Description: 利用高斯塞得尔迭代法解线性方程组，改算法能对所有类型的线性方程组进行求解，且收敛速度快！-Seoul was the use of high-CEDE?O iteration solving linear equations, the algorithm can be changed for all types of linear equations to solve, and fast convergence! Platform: |
Size: 1024 |
Author:chenzuo |
Hits:
Description: 采用一种原地不动法求解矩阵的逆，不仅节省计算时的存储容量，且计算收敛速度快！-Fixed in situ using a matrix inverse method, not only saves the calculation of storage capacity, and fast convergence calculation! Platform: |
Size: 1024 |
Author:chenzuo |
Hits:
Description: 应用模拟退火方法求解非线形方程，其计算量较小且收敛速度快。-Application of simulated annealing method for solving non-linear equation, which is calculated the volume of the smaller and fast convergence. Platform: |
Size: 1024 |
Author:上官青云 |
Hits:
Description: 提出了一种基于小波神经网络整定的PID 控制方法。由于小波变换具有良
好的时频局部特性,神经网络具有强大的非线性映射能力,自学习、自适应等优势,采用规
范正交的小波函数作为神经网络的基函数构成小波神经网络,该网络兼有小波函数的紧
支性、波动性以及神经网络的非线性映射能力,自学习、自适应能力等优点,渗碳炉控制实
验结果表明,用该方法整定的PID 控制系统收敛速度快,逼近精度高,鲁棒性好-Based on wavelet neural network-tuning of PID control methods. Since the wavelet transform has good time-frequency localization properties, neural network has strong ability of nonlinear mapping, self-learning, adaptive and other advantages, the use of standardized orthogonal wavelet function as a neural network constitutes a wavelet basis function neural network, the network a combination of compactly supported wavelet function, and volatility as well as the neural network nonlinear mapping ability, self-learning, adaptive capacity, etc., carburizing furnace control experimental results show that using this method of tuning PID control system for fast convergence approximation of high accuracy, good robustness Platform: |
Size: 192512 |
Author:guole |
Hits:
Description: 若不希望用与估计输入信号矢量有关的相关矩阵来加快LMS算法的收敛速度，那么可用变步长方法来缩短其自适应收敛过程，其中一个主要的方法是归一化LMS算法（NLMS算法），变步长 的更新公式可写成
W（n+1）=w（n）+ e（n）x（n）
=w（n）+ （3.1）
式中， = e（n）x（n）表示滤波权矢量迭代更新的调整量。为了达到快速收敛的目的，必须合适的选择变步长 的值，一个可能策略是尽可能多地减少瞬时平方误差，即用瞬时平方误差作为均方误差的MSE简单估计，这也是LMS算法的基本思想。
-Want to estimate if the input signal vector and the relevant matrix to speed up the convergence rate of LMS algorithm, then the variable step size method can be used to shorten its adaptive convergence process, one of the main method is normalized LMS algorithm (NLMS algorithm) , variable step-size update formula can be written W (n+ 1) = w (n)+ e (n) x (n) = w (n)+ (3.1) where, = e (n) x (n) the right to express filter update vector iterative adjust the volume. In order to achieve the purpose of fast convergence, we must choose the appropriate value of variable step size, a possible strategy is as much as possible to reduce the instantaneous squared error, which uses the instantaneous squared error as the mean square error MSE of the simple estimate, which is the basic LMS algorithm思想. Platform: |
Size: 3072 |
Author:闫丰 |
Hits:
Description: 采用一种快速收敛变步长LMS（Least mean square ） 自适应最小均方算法matlab源程序，其中算法所做的工作是用FIR 滤波器的预测系统，对IIR系统进行预测，如果阶数越高越能逼近被预测系统。-Using a fast convergence of variable step size LMS (Least mean square) adaptive least mean square algorithm matlab source, one of algorithm is the work done by FIR prediction filter systems, prediction of IIR systems, if the higher order the more it can be prediction system approximation. Platform: |
Size: 1024 |
Author:杨思科 |
Hits:
Description: 一种使用牛顿迭代的超分辨算法，该算法以2的对数提高传统Landweber算法的运算速度，附带文章。-The problem of poor resolution of acquired image in the passive millimeter wave imaging stems mainly from antenna size limitations, thus necessitating efficient post-processing to achieve resolution improvements. A novel image super-resolution algorithm, Regularized-Newton-Residual (RNR) algorithm, is proposed for Passive Millimeter wave imaging (PMMW). First Newton inversion algorithm is introduced into the field of image restoration. The iterative scheme of Newton algorithm is deduced based on normal equation. Then, residual method is employed to achieve better performance and implement spectrum extrapolation. Experimental results demonstrate the algorithm is insensitive to noise distribution. Furthermore it has high super-resolution rate and fast convergence speed. Platform: |
Size: 6144 |
Author:姜正茂 |
Hits:
Description: 本程序提出了变步长自适应滤波算法的步长调整原则:即在初始收敛阶段或未知系统参数发生变化时,步长应比较大,以便有较快的收
敛速度和对时变系统的跟踪速度 而在算法收敛后,不管主输入端干扰信号v ( n) 有多大,都应保持很小的调整步长以达到很小的稳态失调噪声. 根据变步长公式编的程序，很有参考价值.
-This procedure, a variable step adaptive filter algorithm step adjustment principle: that in the initial convergence phase or unknown system parameters change, the steps should be relatively large in order to have fast convergence speed and time-varying systems tracking speed in convergence, no matter the main input interference signal v (n) how much should be adjusted to maintain a small step to achieve a small steady state misadjustment noise. compiled according to the formula variable step procedure useful reference. Platform: |
Size: 1024 |
Author:韩一广 |
Hits:
Search - fast convergence