Get the latest tech news
Understanding Gaussians
The **Gaussian distribution**, or **normal distribution** is a key subject in statistics, machine learning, physics, and pretty much any other field that deals with data and probability.
To come up with the density function, remember the aim we started with: we want the distribution to have a definite scale, some area where almost all of the probability mass is concentrated. (right) The reduced version we will derive below.From the multiplication diagram, we see that $\gc{\Sig}$ contains a number of zero columns which essentially ignore the corrsponding dimensions of $\s'$. Finally, if we want to condition on more than one element of $\x$, we could repeat the same proof structure any dimension of hyperplane, but it’s simpler to just apply the theorem multiple times.
Or read this on Hacker News