Вопрос

For example, you can reorder a softmax + nl (negative likelihood) to log_softmax + nll (negative log-likelihood)

Essentially changing log(softmax(x)) to softmax(log(x))

However, what are the rules to reordering logging of things?

Это было полезно?

Решение

In general, you cannot reorder like that. The example you give is a very special case that only works because softmax is based on the exponential function, which is the inverse function of the natural logarithm.

Лицензировано под: CC-BY-SA с атрибуция
Не связан с datascience.stackexchange
scroll top