搜索资源列表
PCG
- 预处理的共轭梯度算法和最速下降法MATLAB算法及源程序.-Preconditioning conjugate gradient algorithm and the steepest descent method MATLAB algorithms and source code.
tiduxiajiang
- 多传感器数据融合的梯度下降法。方法较为简单,代码基本可以实现滚转角与俯仰角的解算,需要再调参数会更精确-Multi-sensor data fusion gradient descent. The method is simple, basic code can roll angle and pitch angle of the solver, you need to re-tune the parameters would be more accurate
linear_regression_with_one_variable
- 自己编写的程序,能够实现单变量的线性回归,随机产生训练样本,利用梯度下降法实现训练过程,并且画出了误差的迭代曲线。-I have written a program that can achieve single-variable linear regression, random training sample using gradient descent method to achieve the training process, and draw the iterative curve
logistic_regression
- 利用逻辑回归实现二分类的matlab程序。随机生成训练样本,利用梯度下降法进行训练,并且在样本图上画出了分类边界。-Logistic regression for binary classification matlab procedures. Randomly generated training samples, the training using the gradient descent method, and is shown in Figure on the sample class
Image-Sharpening
- 在matlabzhong 运用5种不同的梯度增强法对图像进行图像锐化-For image sharpening use five different gradient Enhancement Act
deepest_descent_method_1D
- 梯度下降法在一维函数中的优化应用,自己原创,可以运行,无任何错误-Gradient descent algorithm applied in a one-dimensional function optimization, and their own original, can run without error.
deepest_descent_method_2D
- 梯度下降法在二维函数中的优化寻优,老师上课的例子,可以运行无误-Gradient descent optimization in a two-dimensional function optimization, teacher in the class example, you can run correctly
SVM-study-for-the-news
- 基于梯度下降法的SVM的实现。适合初学者-Gradient descent method to achieve SVM. Suitable for the news.
TOTO_NeuralNetwork_v2
- 全手工Java书写的完全面向对象结构的人工神经网络,现版本,仅实现BP神经网络以及普通梯度下降法,但结构精炼,易于扩展,本人正在书写稀疏自编码用于图像处理,但本版本尚未涵盖。将在以后的版本中上传。(附带CSV输入)-Neural Network Programmed by JAVA, the key contribution of this Project is 100 OO based, readers can easily figure out how to add more things
td_fwi_grads_exa
- 声波方程伪谱法正演模拟,伴随态法波场残差逆推,计算全波形反演梯度-With the state of the residual gradient acoustic wave equation is calculated based on the return, full waveform inversion basic step.
code
- 利用梯度投影法解决有约束的目标函数优化问题-Gradient projection method for solving constrained optimization problem objective function
LogisticRegression
- 用python实现逻辑回归,实现了梯度下降,随机梯度下降法收敛。-Realized the logistic regression by python, using gradient decescent, stochastic gradient decescent to diverge to the final point.
HousePrice(gradient-descent)
- 利用机器学习算法实现南京房价预测。已知2000年至2013年的南京房价,利用梯度下降法预测2014年南京房价。-Nanjing using machine learning algorithm to predict prices. Known 2000-2013 Nanjing prices, using the gradient descent method to predict 2014 Nanjing prices.
Exercise8
- LES算法。包含梯度下降法优化算法,并且以图示每一步迭代权值如何更新。-LES algorithms. Contains gradient descent optimization algorithm, and with each iteration illustrates how to update the weights.
image-process
- 5*5区域的邻域平均法,5*5中值滤波法,图像的锐化(Sobel,Laplacian算子),Roberts梯度锐化算法-neighbourhood averaging and median filtering of 5*5area, Image sharpening(include Sobel,Laplacian),and robert gradient sharpening algorithm
chap3
- 基于梯度下降法的RBF神经网络算法设计仿真-Design and Simulation of RBF neural network algorithm based on gradient descent method
l1-algorithm
- 该软件包包含了合并执行在MATLAB9升-1的最小化算法。每个函数都使用一组参数是一致的(如停止准则和公差)与我们的基准脚本接口。 正交匹配追踪:SolveOMP.m 原对偶内点法:SolvePDIPA.m 梯度投影:SolveL1LS.m 同伦:SolveHomotopy.m 迭代阈值:SolveSpaRSA.m 近梯度:SolveFISTA.m TFOCS:SolveTFOCS.m SesopPCD:SolveSesopPCD.m 原始增强拉格朗日乘子:S
CV-model-code2
- CV模型是一种重要的图像分割模型,本文针对其收敛速度慢、效率低的缺点提出一种求解CV模型的新方法.首先将CV模型的能量泛函改写成与原来有相同稳定解的总变分公式形式,然后使用对偶公式法求总变分公式的极小值,再在其中引入一速度项以加快模型的收敛速度.新方法一方面克服了梯度下降法要求时间步长小、迭代次数多的缺点,经过较少次的迭代就能收敛,减少了迭代计算的次数-CV model is one of the most important image segmentation model and disad
fastest
- 最速下降法求解方程f=1/2x *A*x+b *x求其极小值点,其中梯度g=Ax-b,下降方向p=-g,x为初始点,eps为精度。 注:本程序只适用于二次方程,即方程的A矩阵不含未知数。-Steepest descent method for solving the equation f = 1/2x * A* x+ b * x seeking the minimum point where the gradient g = Ax-b, the descent direction p =-
Powell
- 鲍威尔优化算法:多维无约束优化算法是在无约束优化算法之一,首先选取一组共轭方向,从某个初始点出发,求目标函数在这些方向上的极小值点,然后以该点为新的出发点,重复这一过程直到获得满意解,其优点是不必计算目标函数的梯度就可以在有限步内找到极值点。 鲍威尔法是以共轭方向为基础的收敛较快的直接法之一,是一种十分有效的算法。-Powell optimization algorithm