Computing the inverse of a matrix is one of the most important operations in machine learning. If some matrix A has shape n-by-n, then its inverse matrix Ai is n-by-n and the matrix product of Ai * A ...
isn't it better to invert it once in the CPU and then put inverted into the uniform? Yeah that's what you usually do in a real game or engine. But it's out of scope of the tutorial to implement an ...