Multsets are sets that allow repetition of elements, therefore account for their frequency of observation. As such, multisets pave the way to a number of interesting possibilities of both theoretical and applied nature. In the present work, after revising the main aspects of traditional sets, we introduce some of the main concepts and characteristics of multisets, which is followed by their generalization to take into account vectors, matrices, functions, scalar fields, and densities. The potential of multisets in pattern recognition and deep learning is also briefly characterized and illustrated.