The illustration we previously saw was that of a three dimensional tensor, yet tensors can appear in many forms. In the following section, we will overview some tensors of different ranks, starting with a tensor of rank zero:
- Scalar: Values simply denote a single numeric value on its own. This can also be described as a tensor of dimension 0. An example of this is processing a single grayscale pixel of an image through a network.
- Vector: A bunch of scalars or an array of numbers is called a vector, or a tensor of rank 1. A 1D tensor is said to have exactly one axis. An example of this is processing a single flattened image.
- Matrix: An array of vectors is a matrix, or 2D tensor. A matrix has two axes (often referred to as rows and columns). You can visually interpret a matrix as a rectangular grid of numbers. An example of this is processing a single grayscale...
