k_logsumexp

An integer, the axis to reduce over (axis indexes are 1-based).

axis

A boolean, whether to keep the dimensions or not. If
<code>keepdims</code> is <code>FALSE</code>, the rank of the tensor is reduced by 1. If
<code>keepdims</code> is <code>TRUE</code>, the reduced dimension is retained with length 1.

keepdims

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.

Interface to 'Keras' <https://keras.io>, a high-level neural
networks 'API'. 'Keras' was developed with a focus on enabling fast experimentation,
supports both convolution based networks and recurrent networks (as well as
combinations of the two), and runs seamlessly on both 'CPU' and 'GPU' devices.

JJ Allaire

keras

R Interface to 'Keras'

Fran<c3><a7>ois Chollet

 RStudio

 Google

Yuan Tang

Daniel Falbel

Wouter Van Der Bijl

Martin Studer

Sigrid Keydana

k_logsumexp function

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:
<a href="https://keras.rstudio.com/articles/backend.html#backend-functions">https://keras.rstudio.com/articles/backend.html#backend-functions</a>.

k_logsumexp: Computes log(sum(exp(elements across dimensions of a tensor))).

Description

Usage

Arguments

Value

Keras Backend