Earticle

This paper describes the result of applying neuro-fuzzy reasoning, which conducts Go term knowledge based on pattern knowledge, to the opening game of Go. We discuss the implementation of neuro-fuzzy reasoning for deciding the best next move to proceed through the opening game. We also let neuro-fuzzy reasoning play against TD(入) learning to test the performance. The experimental result reveals that even the simple neuro-fuzzy reasoning model can compete against TD(入) learning and it shows great potential to be applied to the real game of Go.

This study aims to redefine the factors of Baduk-strengh which is closely related to the interest and curiosity in the game of baduk, and to show the model of Baduk-strength test on the basis of the problems appeared in the present system. It classifies the factors of BS into "Baduk internal factors" and "Baduk external factors." The former consists of knowledge, suilgi(move-reading), and evaluation, while the latter the psychological factor and the environmental factor. The internal one is divided into cognitive elements and behavior elements. The present BS test turned out to have some problems: the lack of divergency in item construction, not verified tests in reliability and validity, problems in criteria establishment, adequacy of the number of items and the time of test, etc. To solve these problems, alternative approaches are presented such as redefining BS components, reconsidering the scope of the test, the method of showing the result of the test, the conversion of the subjects' faculty to the step of BS, and the use of CAT(Computerized Adaptive Testing) method is proposed based on 'item response theory' to develop the model of objective BS tests.