Question

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?

Was it helpful?

Solution

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.

Licensed under: CC-BY-SA with attribution
Not affiliated with datascience.stackexchange
scroll top