The problems of self-learning are discussed, and a general method of solving these problems is described. Performance criteria for evaluating the quality of self-learning are given, and the algorithms for self-learning which minimize the proposed performance criteria are found. The ideas of optimal algorithms are introduced. In the conclusion, the special nature of the problems of self-learning is discussed.
No takes yet. Share an insight, caveat, or question.
Ya. Ζ. Tsypkin (1968) studied this question.
Synapse has enriched one closely related paper. Consider it for comparative context: