This funciton is deprecated. Please use tensorflow::tf$reduce_logsumexp()
.
k_logsumexp(x, axis = NULL, keepdims = FALSE)
The reduced tensor.
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
keepdims
is FALSE
, the rank of the tensor is reduced by 1. If
keepdims
is TRUE
, the reduced dimension is retained with length 1.
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://tensorflow.rstudio.com/reference/keras/index.html#backend.
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.