Difference between revisions of "RenormLayer.m"
(Normalise sequential blank lines) |
(Update function See also links and function index membership) |
||
| Line 11: | Line 11: | ||
==See also== | ==See also== | ||
| − | [[Neural network module]] | + | [[dist_net.m]], [[dist_vet.m]], [[logsLayer.m]], [[Neural network module]] |
''Version 2.8, authors: [[Ilya Kuprov]], [[Jake Keeley]]'' | ''Version 2.8, authors: [[Ilya Kuprov]], [[Jake Keeley]]'' | ||
Latest revision as of 19:40, 6 June 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
dist_net.m, dist_vet.m, logsLayer.m, Neural network module
Version 2.8, authors: Ilya Kuprov, Jake Keeley
