NIRNAY: An AI Chess Engine Based on Convolutional Neural Network, Negamax and Move Ordering

Chess, one of the world's most popular games, has come a long way from the time it has gone digital. Now almost every year, efforts are being made to improve existing engines or towards building powerful engines on some new algorithms. All these efforts are making the game difficult yet interesting for chess lovers. These chess engines, created using different algorithms like pruning, Monte Carlo Search Tree, are so powerful that they are known to defeat some of the world-famous chess grandmasters using their high computational power, by predicting the most optimized legal chess move. But still, there is a large-scale hidden opportunity to explore the applications of machine learning to create stronger and more efficient engines. In this paper, we have proposed an innovative contribution, depicting the application of Convolutional Neural Networks (CNN) and Negamax approach in building a robust engine.