1400
правок
О бритве Оккама: различия между версиями
Перейти к навигации
Перейти к поиску
нет описания правки
Нет описания правки |
Нет описания правки Метка: отменено |
||
| Строка 1: | Строка 1: | ||
Распространенная современная интерпретация "бритвы Оккама" для широкого круга задач не работает даже в математике: | Распространенная современная интерпретация "бритвы Оккама" для широкого круга задач не работает в общем случае даже в математике: | ||
"In machine learning, this is [Occam’s razor] often taken to mean that, given two classifiers with the same training error, the simpler of the two will likely have the lowest test error. Purported proofs of this claim appear regularly in the literature, but in fact there are many counter examples to it, and the “no free lunch” theorems imply it cannot be true. We saw one counter-example in the previous section: model ensembles. The generalization error of a boosted ensemble continues to improve by adding classifiers even after the training error has reached zero."<ref>Domingos P. A few useful things to know about machine learning // Communications of the ACM. Vol. 55 (10). 2012. n. 11.</ref> | "In machine learning, this is [Occam’s razor] often taken to mean that, given two classifiers with the same training error, the simpler of the two will likely have the lowest test error. Purported proofs of this claim appear regularly in the literature, but in fact there are many counter examples to it, and the “no free lunch” theorems imply it cannot be true. We saw one counter-example in the previous section: model ensembles. The generalization error of a boosted ensemble continues to improve by adding classifiers even after the training error has reached zero."<ref>Domingos P. A few useful things to know about machine learning // Communications of the ACM. Vol. 55 (10). 2012. n. 11.</ref> | ||