This paper presents an algorithm of playing game tic-tac-toc. This algorithm is learned by a modified neural network (NN), which is trained by an improved genetic algorithm (GA). In the proposed NN, the neuron has two activation functions and exhibits a node-to-node relationship in the hidden layer that enhances the learning ability of the network. It will be shown that the proposed NN and GA provide a better performance than the traditional approach. ; Author name used in this publication: P. K. S. Tam ; Author name used in this publication: Y. S. Lee ; Centre for Multimedia Signal Processing, Department of Electronic and Information Engineering ; Author name used in this publication: F. H. F. Leung