Нашли опечатку? Выделите ее мышкой и нажмите Ctrl+Enter
Название: The Maximum Entropy Principle as a Consequence of the Principle of Laplace
Автор: Hadjisavvas N.
The maximum entropy principle states that the probability distribution which best rePresents our information is the one which maximizes the entropy with the given evidence as constraints. We prove that this principle is implied from the Laplace principle of equiprobabilities applied to the set S of all N-term sequences of results which are compatible with the given evidence. We generalize to the "information gain" method of Kullback.