The intention of this class is to allow you to pay up front (at construction)
the compute cost of converting the RGB values in a BufferedImage into a derived form.
Creates full connectivity within layer - each neuron with all other
within the same layer with the specified weight and delay values for all
conections.
Starts learning with specified learning rule in new thread to learn the
specified training set, and immediately returns from method to the current thread execution
Starts the learning with specified learning rule in the current running
thread to learn the specified training set, and returns from method when network is done learning