Statement Judgment Algorithm of Go Game Based on Deep Adaptation Network

In the paper, the characteristics of the statement judgment of Go game are analyzed comprehensively and systematically. It selects the patterns and influence function in the expert system to give the characteristic values. Combining the features and passing them to the deep adaptation network, it can use the existing disk and result labels to train the network in a supervised learning mode to generate a complete disk judgment and evaluation model. Through a public data set and a private data set, an optimal evaluation network with 8 layers and 200 iterations is obtained finally. The experimental results prove the feasibility and effectiveness of the algorithm. And the algorithm provided in the paper solves the problem that the current Go evaluation algorithm parameters are difficult to train and optimize.