Entropy and Algorithm of the Decision Tree for Approximated Natural IntelligenceстатьяИсследовательская статья
Информация о цитировании статьи получена из
Web of Science,
Scopus
Статья опубликована в журнале из списка Web of Science и/или Scopus
Дата последнего поиска статьи во внешних источниках: 4 сентября 2018 г.
Аннотация:An actual task is the classification of knowledge of a specified subject area, where it’s represented not as information coded in a certain manner, but in a way close to the natural intelligence, which structures obtained knowledge according to a different principle. The well-known answers to the questions should be classified so that the current task could be solved. Thus a new method of decision tree formation, which is approximated to the natural intelligence, is suitable for knowledge understanding. The article describes how entropy is connected to knowledge appearance, classification of previous knowledge and with definitions used in decision trees. The latter is necessary for comparing the traditional methods with the algorithm of the decision tree obtaining approximated to the natural intelligence. The dependency of entropy on the properties of element subsets of a set has been obtained.