We describe the development of a Go playing computer program that combines the use of hard Artificial Intelligence (AI) techniques (alpha-beta search trees) with soft AI techniques (neural networks). The concept is based on a model of human play where selection of plausible moves is made using a gestalt process based on experience and the plausible moves… (More)
This paper investigates the application of neural network techniques to the creation of a program that can play the game of Go with some degree of success. The combination of soft AI, such as neural networks, and hard AI methods, such as alpha-beta pruned minimax game tree searching, is attempted to assess the usefulness of blending these two different… (More)
We describe a hybrid Artificial Intelligence (AI) approach combining soft AI techniques (neural networks) and hard AI methods (alpha-beta game tree search), in an attempt to approximate human play more accurately, in particular with reference to the game of Go. The program is tested and analysed by play against another Go playing program and it is shown… (More)
An alternative game tree search method is presented using a novel genetic algorithm. This is enhanced by the inclusion of Go specific knowledge learnt with neural network techniques developed from previous research. This hybrid algorithm is compared to a traditional alpha-beta search method, MTD(f), and a series of tests and results are presented.