What are the five layers in the ANFIS model and what is the function of each layer?

ANFIS has five layers: fuzzification, output of the product of membership values, normalization of firing strengths, Takagi-Sugeno rule computation, and final summation. Layer 1 converts each input into linguistic membership grades using membership functions. Layer 2 multiplies the incoming membership degrees to create firing strengths. Layer 3 normalizes those strengths. Layer 4 computes each rule's weighted consequent using Takagi-Sugeno if-then rules. Layer 5 sums all weighted rule outputs to give the final ANFIS output.

The source describes ANFIS as a hybrid model with five types of layers, each containing nodes. In Layer 1, each input is converted into a linguistic form using a membership function, such as triangular, trapezoidal, or bell membership functions, and the output is the membership grade of that input. In Layer 2, each node multiplies the linguistic membership values received from the previous layer, producing a firing strength for each rule. In Layer 3, each node normalizes the firing strengths by dividing an individual rule strength by the sum of all rule strengths, giving a normalized weight. In Layer 4, Takagi-Sugeno type if-then rules are used to compute each node's output as the normalized firing strength multiplied by a rule consequence, where the consequence is a linear function of the inputs. In Layer 5, a single summation node adds all incoming weighted rule outputs to produce the final ANFIS output.