Playing Tic-Tac-Toe Using Genetic Neural Network with Double Transfer functions

Scientific Research Publishing, Inc.
Publication Type:
Journal Article
Journal of Intelligence Learning Systems and Application, 2011, 3 (1), pp. 37 - 44
Issue Date:
Full metadata record
Computational intelligence is a powerful tool for game development. In this paper, an algorithm of playing the game Tic-Tac-Toe with computational intelligence is developed. This algorithm is learned by a Neural Network with Double Transfer functions (NNDTF), which is trained by genetic algorithm (GA). In the NNDTF, the neuron has two transfer functions and exhibits a node-to-node relationship in the hidden layer that enhances the learning ability of the network. A Tic-Tac-Toe game is used to show that the NNDTF provide a better performance than the traditional neural network does.
Please use this identifier to cite or link to this item: