Singular Value Decomposition summary
- Singular value decomposition breaks our matrix down into a set of smaller
components.
- The algorithm alters these components to reduce the number of dimensions.
- Recombines them into a matrix of the same shape as our original, so we can
again use it as a lookup grid.
- The matrix we get back is an approximation of the content-word-transcript matrix
we provided as input, and looks much different from the original.