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?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.