Application of Varieties of Learning Rules in Intuitionistic Fuzzy Artificial Neural Network

In this work, the decision-making models based on Artificial Neural Network (ANN) are presented. These models accept argument pairs called weighted geometric and weighted averaging pairs, where one component is used to induce an ordering over the second component, which are intuitionistic fuzzy values, and then aggregated. The decision-making problem is addressed by the proposed method of a novel ANN, where the inputs take the form of intuitionistic fuzzy matrices and are resolved using the Perceptron, Hebbian, and Delta Learning Rules. To demonstrate the usefulness and applicability of the created method in comparison to the conventional decision-making models, a numerical example using several ranking algorithms is provided at the end. The new method of intuitionistic fuzzy ANN, which is a groundbreaking work in the field of intuitionistic fuzzy ANN, proves to be more effective than the previous methods because it eliminates the unimportant decision alternatives from the system of available decision alternatives for inputs such as intuitionistic fuzzy matrices.