I have multiple image sequences, each of which contains an animation of two moving dots. The trajectory of the dots in a sequence is always cyclic (not necessarily circular). There are two types of sequences. In some sequences the two dots are moving in phase but in the other sequences they are moving out of phase.
Is it possible to classify these two types of sequences using a neural network? What is the simple and feasible neural network structure for this classification?
Here's an example set of animations. The in-phase patterns are in the above row and the out-of-phase patterns are in the bottom row.