how can calculate linear regression coefficent with neural network and other way?

2 次查看（过去 30 天）
zohreh saba
zohreh saba 2015-10-3
回答： Star Strider 2015-10-3
I am analysing data with 9inputs and one output. I want neural network to predict the mathematical model or a regression equation. For instance I have 9 inputs as x1, x2, x3, x4, x5, x6,x7,x8,x9 and one output y. Now I want that network provide me an equation in the form.
y= a1*x1 + a2*x2+ a3*x3 + a4*x4 + a5*x5+ a6*x6+a7*x7+a8*x8+a9*x9+a0
How I can get the coefficient in above equation? I have 8 state for above equation
for example
2.78 =3.6000a1+a299.0000 +a3 93.0000 +a4 97.0000 +a5 87.0000+a6 23.7319+a7 24.5026+a8 31.6361+a9 0.8939
;
;
;
I have 7 above equation.
Regards and thanks in advance.

请先登录，再回答此问题。

采纳的回答

Star Strider
Star Strider 2015-10-3
You don’t need a neural net to solve that problem. You can do it in core MATLAB:
a = [x1(:) x2(:) ... x9(:) ones(length(x))]\y(:);
The coefficients will be in the ‘a’ vector.

更多回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Linear Regression 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