Consider a standard additive model consisting of rules of the form of
If $x$ is $A_i$ AND $y$ is $B_i$ THEN $z$ is $C_i$. Given crisp inputs $x=x_0, \: y=y_0$ the output of the model is
- $z=\Sigma_i \mu_{A_i} (x_0) \mu_{B_i} (y_0) \mu_{C_i} (z)$
- $z=\Sigma_i \mu_{A_i}(x_0) \mu_{B_i} (y_0)$
- $z=\text{centroid } (\Sigma_i \mu_{A_i} (x_0) \mu_{B_i} (y_0) \mu_{C_i} (z))$
- $z=\text{centroid } (\Sigma_i \mu_{A_i} (x_0) \mu_{B_i} (y_0)$