Multivariate Linear Regression code

1 次查看（过去 30 天）
b
b 2012-5-18
In my hand, 30 samples of 4 features and 30 outputs. i want to learn the regression equation of these as;
theta=theta(0) + theta(1) x(1)+ ... + theta(4) x(4)
I am using gradient descent algorithm for this regression analysis. there are three main equations;
for m=1:30;
cost function= J(theta(0)..,theta(4))=1/2m * sum(h(theta)x - y) ^2
%sum is from 1 to m. x and y are from 1 to m.
theta(j) := theta(j) - alpha (derivative/derivative theta(j)) J(theta(j)
Thanks
  1 个评论
b
b 2012-5-18
Sorry for that, i have 30 samples of 3 features output also.
input=30x4 matrix
output=30x3 matrix

请先登录，再进行评论。

请先登录，再回答此问题。

回答（2 个）

b
b 2012-5-18
If there is a chance of doing this with 3 features output, it will be superb. otherwise, it's also OK.
bym
bym 2012-5-18
I really do not understand your question, but perhaps this is what you are looking for:
x = rand(30,4);
>> y = rand(30,1);
>> X = [ones(30,1) x];
>> theta = X\y
theta =
0.6702
0.1183
-0.4163
-0.1072
-0.1355
  1 个评论
b
b 2012-5-18
Actually, no. I have x and y values and theta values will be obtained from the equation.
I want the cost function code.

请先登录，再进行评论。

类别

在 Help Center 和 File Exchange 中查找有关 Polynomials 的更多信息

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by