This function is more numerically stable than log(sum(exp(x))). It avoids overflows caused by taking the exp of large inputs and underflows caused by taking the log of small inputs.
k_logsumexp(x, axis = NULL, keepdims = FALSE)
A tensor or variable.
An integer, the axis to reduce over (axis indexes are 1-based).
A boolean, whether to keep the dimensions or not. If
The reduced tensor.
This function is part of a set of Keras backend functions that enable lower level access to the core operations of the backend tensor engine (e.g. TensorFlow, CNTK, Theano, etc.).
You can see a list of all available backend functions here: https://keras.rstudio.com/articles/backend.html#backend-functions.