Machine Learning, Game Play, and Go

The game of go is an ideal problem domain for exploring machine learning: it is easy to define and there are many human experts, yet existing programs have failed to emulate their level of play to date. Existing literature on go playing programs and applications of machine learning to games are surveyed. An error function based on a database of master games is defined which is used to formulate the learning of go as an optimization problem. A classification technique called pattern preference is presented which is able to automatically derive patterns representative of good moves; a hashing technique allows pattern preference to run efficiently on conventional hardware with graceful degradation as memory size decreases. Contents 1 Machine Learning 6 1.1 What is machine learning? : : : : : : : : : : : : : : : : : : : : : : : : : : 6 1.2 Learning as optimization : : : : : : : : : : : : : : : : : : : : : : : : : : : 7 1.3 The Bias of Generalization : : : : : : : : : : : : : : : : : : :..