Figure 3.

Example image of a perceptron. In this case, $x_1,x_2,x_3$ are the inputs. The weights are $w_1,w_2$ and $w_3.b$ is the perceptron bias. $z$ is the weighted sum of the network inputs and the bias. $g(z)$ is the activation function. $\hat{y}$ is the perceptrons output.