METHOD FOR INTERPRETATION OF ARTIFICIAL NEURAL NETWORKS

摘要

This technical solution, in General, relates to the field of computer technology, and in particular to methods and systems for interpreting the operation of models of artificial neural networks. A method for interpreting artificial neural networks, in which at least one artificial neural network is previously trained on a set of objects; at least one decision tree is formed for each layer of the trained neural network, and the decision tree receives as input data the activation of the corresponding layer obtained when passing through the neural network of the object from the existing data set; using the decision trees, predict the same answer that the trained artificial neural network gives out on this object; then, for each object, an ordered sequence of leaf numbers generated at the previous step of decision trees is obtained; then form a set of rules that predicts the sequence of leaf numbers for the object. The technical result is an increase in the quality and accuracy of the interpretation of the operation of an artificial neural network.