The problem: I want to classify a trajectory if it has some properties, for example I want to create a simple 0/1 classifier for circular trajectories. If a target is moving in a circular trajectory the network should produce 1, if not it should produce 0.
My input and data set: what I have is data set with cartesian coordinates in 2d so x,y,Vx,Vy. I have a dataset of 10000 trajectory, 5000 circular, 5000 rectilinear. So I feed the network with a tensor [10000, 4, 1]
The question: I'm trying to use a network with three layers, input layer with 4 neurons, hidden layer with 2 LTSM and one fc layer with sigmoid activation function. Is it possible to feed the network with a tensor [4x1] each time? Or do I need to provide the information in batches? Or what? Is the design of my basic network correct?