matlab多(慢,但更详细)变量的梯度下降法求解线性回归问题我要分享

The gradient descent method for MATLAB (slow, but

matlab 回归 详细 线性 求解 问题 梯度 下降 变量

关注次数: 314

下载次数: 0

文件大小: 1.48 kB

代码分类: 其他

开发平台: matlab

下载需要积分: 2积分

版权声明:如果侵犯了您的权益请与我们联系,我们将在24小时内删除。

代码描述

中文说明:应用背景这个多变量(慢)变化的文件的概要;主要。M是文件的准备,我们的算法所需的所有数据,饲料数据给另一个函数实际上已经实施的算法,然后显示我们的结果。梯度,是具有梯度功能的文件,并在其上实现梯度下降。成本:我是一个简单的文件,它有一个函数,它的参数计算的值的成本函数。此源代码的另一个重要特点是,标准化也包括在内,可以打开或关闭所需的。如果你只是想看一下性能,就包含了样本数据测试文件。关键技术这是一个多变量的算法,该算法需要多个步骤,向当地的最小的功能收敛到快速的解决方案。这个代码是你的算法工具箱-测试数据包括-今天-下载,而你仍然可以。


English Description:

Application backgroundOutline of included files for this multiple-variable (slow) variation:  main.m is the file that prepares all the data that is required for our algorithm, feeds this data to another function which actually has the implementation of the algorithm in it, and then shows us the results. gradient.m is the file that has the gradient function and the implementation of gradient descent in it. cost.m is a short and simple file that has a function that calculates the value of cost function with respect to its arguments. Another important feature of this source code is that normalization is also included and can be turned on or off as desired. The sample data test file is included if you simply want to look at the performance. Key TechnologyThis is the Multiple variable variati


代码预览