Difference between revisions of "RenormLayer.m"
(→See also) |
(Normalise sequential blank lines) |
||
| Line 12: | Line 12: | ||
==See also== | ==See also== | ||
[[Neural network module]] | [[Neural network module]] | ||
| − | |||
''Version 2.8, authors: [[Ilya Kuprov]], [[Jake Keeley]]'' | ''Version 2.8, authors: [[Ilya Kuprov]], [[Jake Keeley]]'' | ||
Revision as of 12:29, 25 April 2026
Renormalisation layer for probability distributions. Makes the mean value across the input vector equal to 1. The mean is used instead of the sum to stay around the sweet spot of single-precision arithmetic.
Syntax
layer=renormLayer()
Outputs
layer - Matlab Deep Learning Toolbox layer object
See also
Version 2.8, authors: Ilya Kuprov, Jake Keeley
