A system for machine learning based on algorithmic probability

The author has previously used algorithmic probability theory (APT) to construct a system for machine learning of great power and generality (1986). The article concerns the design of sequences of problems to train this system. APT provides a general model of the learning process that makes it possible to understand and overcome many of the limitations of existing programs for machine learning. Starting with a machine containing a small set of concepts, use is made of a carefully designed sequence of problems of increasing difficulty to bring the machine to a high level of problem-solving skill. The use of training sequences of problems for machine knowledge acquisition promises to yield expert systems that will be easier to train and free of the brittleness that characterizes the narrow specialization of present-day systems of this sort. It is also expected that this research will give needed insight into the design of training sequences for human learning