Let's assume that we have a regression problem. Our input is just binarized image that contains a single rectangle and we want to predict just a float number. Actually, this floating-point number depends on rectangle angle, rectangle size and rectangle location. Is this problem can be solved by a neural network?
I think, it can not be solved by a neural network, because rectangle angle, size and location are latent variables and without learning these latent variable, above problem can not be solved. What do you think?