How Neurons Work

How neurons really work

Let’s look at how a neuron works. It takes an electric input and sends out another electrical signal. This looks exactly like the classifying or predicting machines we looked at earlier, which took an input, did some processing, and produced an output.

So, can we represent neurons as linear functions, like we did before? It’s a good idea, but no. A biological neuron doesn’t produce an output that is a simple linear function of the input. That is, its output does not take the form:

$$\text{Output = (constant$\cdot$input) + (maybe)\hspace{0.4mm} another\hspace{0.4mm} constant)}$$

$$$$

Observations suggest that neurons don’t react readily, but instead suppress the input until it has grown so large that it triggers an output. We can think of this as a threshold that must be reached before any output is produced. It’s like water in a cup—the water doesn’t spill over until it has first filled the cup. Intuitively, this makes sense. The neurons don’t want to pass tiny noise signals. They only want to pass emphatically strong, intentional signals. The following image illustrates this idea of producing an output signal only if the input is sufficiently dialed up to pass a threshold.