Integrate and Fire Network:

	The following is a representation of what occurs in the integrate-and-fire model that
  is being used.  Each neuron has a different threshold level that needs to be reached in order
  for that neuron to fire.  If the neuron recieves input but doesn't fire, it's potential is
  raised but has some amount of decay over time.

	KEY:	-GRAY is an inactive neuron
		-RED is an actively firing neuron
		-BLUE is a neuron in its refractory state

	It would be easy to assume that when one neuron fires all other neurons connected
  to it would do the same. This is not the case, however. In a biologically realistic
  neural network, it often takes multiple input signals in order for a neuron to propagate
  a signal. A simple way to make this task easier is to have multiple input signals going
  from one neuron to the next, increasing the effect of one firing by however many connection
  there are. In the computer simulation, this is done by adjusting the weights (or connections)
  between each neuron.
  	In the computer simulation of a neural network, neurons mimic neural biology through a
  technique known as integrate-and-fire. Every neuron has a certain threshold at which it goes from
  stable to firing.  Reaching or exceeding this threshold level is what must be accomplished to
  successfully produce an output signal. When a cell reaches its threshold and fires, its signal
  is passed onto the next neuron, which may or may not cause it to fire.  If the neuron does not fire, its
  potential will be raised so that if it receives another input signals within a certain time
  frame, it will be more likely to fire. This increased potential to fire doesn't last for long though,
  as the potential starts to dampen soon after the input is received. If the neuron does fire, then
  the signal will be propagated onto the next neuron. When this happens, the just-fired neuron goes 
  into a refractory state, in which it doesn't respond to or propagate input signals from other neurons.