I’ve been struggling to understand how the word “tensor” is used in AI because its use in mathematics, physics, and engineering seems different. This comment cleared it up for me.

is the most helpful explanation I can find after a hour or two of googling.

So in machine learning / data processing a tensor appears to be simply defined as a multidimensional numerical array. An example of such a 3D tensor would be 10001000 video frames of 640×480640×480 size. A usual n×pn×p data matrix is an example of a 2D tensor according to this definition.

This is not how tensors are defined in mathematics and physics!