Solution to the Tic-Tac-Toe Problem Using Hamming Distance Approach in a Neural Network

Abstract

Paper focuses on developing an algorithm using a Hamming Distance Classifier in Neural Networks to find the most optimal move to be made in the Tic-Tac-Toe problem such that the game always ends in a win or a draw. The basic step involves an eight-class Hamming network which has nine inputs corresponding to each cell of the grid and eight outputs respectively. The algorithm computes the Hamming Distance of the current input configuration as compared to the weight matrix and the maximum of the output corresponds to the minimum distance. The iterative step is carried out to anticipate the next move for every possible current move. The hamming distance of all the iterations is added to basic step and the gross maximum gives the most profitable move. The algorithm proceeds such that the neural network prefers to itself win rather than preventing the opponent from winning in least possible moves.