What does z=x-mu/sigma stands for?
I know that the notation N(μ,σ) stands for a normal distribution. But I'm reading the book "An Introduction to Variational Autoencoders" and in it, there is this notation:
N(z;0,I) What does it mean?
Z=x-mu/sigma means that z has a (multivariate) normal distribution with 0 mean and identity covariance matrix. This essentially means each individual element of the vector z has a standard normal distribution.