Remarks on some learning algorithms

Abstract

In this paper we present some problems concerning artificial intelligence. In the first two points there are presented algorithmic and heuristic procedures, which are applied in solving problems and making optimal decision for the fixed states as follows: beginning state, set of all states of a problem, subset of final states. The fundamental part of the paper discusses three leaming-algorithms: ID3, AQ and backpropagation, owing to which computer basing on a given sample is to create a general formula or rule and to make a decision which is a solution of the problem. The last section of the paper includes a short description of the predictive accuracy of the algorithms.