Principal component analysis-matlab

  • Thread starter Thread starter nikki92
  • Start date Start date
  • Tags Tags
    Component
nikki92
Messages
37
Reaction score
0

Homework Statement


How do I find the error of the PCA?

||x1hat - x1||^2 + ...+ ||xnhat-xn||^2 so xnhat is the pca one. What is xn?
 
Last edited:
Physics news on Phys.org
can you elaborate more? having some trouble guessing what your notation means.
 
Basically x= randn(100,15)
x_centered=(eye(100)-(1/100)*ones(100,100))*x to subtract the mean to center the data
[s,d,v]=svd(x_centered);

I need to find the principal components
which just the eigenvalues but according to my professor {divi}for i = 1 to 15.
Then I am asked what is the pca with 3, 4, 5 components. For 3 components is it just [d1v1 d2v2 d3v3]

Then I am asked to find the mse of it. I am confused what do I compare the PCA of 3 components to to take the F- norm?
 
Last edited:
Prove $$\int\limits_0^{\sqrt2/4}\frac{1}{\sqrt{x-x^2}}\arcsin\sqrt{\frac{(x-1)\left(x-1+x\sqrt{9-16x}\right)}{1-2x}} \, \mathrm dx = \frac{\pi^2}{8}.$$ Let $$I = \int\limits_0^{\sqrt 2 / 4}\frac{1}{\sqrt{x-x^2}}\arcsin\sqrt{\frac{(x-1)\left(x-1+x\sqrt{9-16x}\right)}{1-2x}} \, \mathrm dx. \tag{1}$$ The representation integral of ##\arcsin## is $$\arcsin u = \int\limits_{0}^{1} \frac{\mathrm dt}{\sqrt{1-t^2}}, \qquad 0 \leqslant u \leqslant 1.$$ Plugging identity above into ##(1)## with ##u...
Back
Top