.TH "/var/www/mlpack.ratml.org/mlpack.org/_src/mlpack-3.3.2/src/mlpack/methods/ann/layer/softshrink.hpp" 3 "Mon Aug 31 2020" "Version 3.3.2" "mlpack" \" -*- nroff -*-
.ad l
.nh
.SH NAME
/var/www/mlpack.ratml.org/mlpack.org/_src/mlpack-3.3.2/src/mlpack/methods/ann/layer/softshrink.hpp
.SH SYNOPSIS
.br
.PP
.SS "Classes"

.in +1c
.ti -1c
.RI "class \fBSoftShrink< InputDataType, OutputDataType >\fP"
.br
.RI "Soft Shrink operator is defined as, \begin{eqnarray*} f(x) &=& \begin{cases} x - \lambda & : x > \lambda \\ x + \lambda & : x < -\lambda \\ 0 & : otherwise. \\ \end{cases} \\ f'(x) &=& \begin{cases} 1 & : x > \lambda \\ 1 & : x < -\lambda \\ 0 & : otherwise. \end{cases} \end{eqnarray*}\&. "
.in -1c
.SS "Namespaces"

.in +1c
.ti -1c
.RI " \fBmlpack\fP"
.br
.RI "Linear algebra utility functions, generally performed on matrices or vectors\&. "
.ti -1c
.RI " \fBmlpack::ann\fP"
.br
.RI "Artificial Neural Network\&. "
.in -1c
.SH "Detailed Description"
.PP 

.PP
\fBAuthor:\fP
.RS 4
Lakshya Ojha
.RE
.PP
The soft shrink function has threshold proportional to the noise level given by the user\&. The use of a Soft Shrink activation function provides adaptive denoising at various noise levels using a single CNN (Convolution Neural Network) without a requirement to train a unique CNN for each noise level\&.
.PP
mlpack is free software; you may redistribute it and/or modify it under the terms of the 3-clause BSD license\&. You should have received a copy of the 3-clause BSD license along with mlpack\&. If not, see http://www.opensource.org/licenses/BSD-3-Clause for more information\&. 
.PP
Definition in file \fBsoftshrink\&.hpp\fP\&.
.SH "Author"
.PP 
Generated automatically by Doxygen for mlpack from the source code\&.