Weeks3 & 4: PCA and covariance
so I wrote this little widget to help you visualize it. So here is the same graph, and what we have here is basically the approximation of the function that we can play with, we can change from, we can change it using these sliders. So right now, we have the approximation that is zero everywhere, so it's basically the zero function, and it's clearly very far from the, from our target function, x minus four absolute value. So let's see what happens if we increase this coefficient. We see that we move, we move the constant to the middle of the function, more or less. Then when we add the second one, we add a sinusoid, and the sinusoid helps us get closer to the function, in some of the regions. It doesn't help us at all here, right, because it's zero, and it stays equidistance, but now if we add the cosine, that helps us also there. So what you see her...