\section{Hard\+Shrink$<$ Input\+Data\+Type, Output\+Data\+Type $>$ Class Template Reference} \label{classmlpack_1_1ann_1_1HardShrink}\index{Hard\+Shrink$<$ Input\+Data\+Type, Output\+Data\+Type $>$@{Hard\+Shrink$<$ Input\+Data\+Type, Output\+Data\+Type $>$}} Hard Shrink operator is defined as, \begin{eqnarray*} f(x) &=& \left\{ \begin{array}{lr} x & : x > lambda \\ x & : x < -lambda \\ 0 & : otherwise \end{array} \\ \right. f'(x) &=& \left\{ \begin{array}{lr} 1 & : x > lambda \\ 1 & : x < -lambda \\ 0 & : otherwise \end{array} \right. \end{eqnarray*} lambda is set to 0.\+5 by default. \subsection*{Public Member Functions} \begin{DoxyCompactItemize} \item \textbf{ Hard\+Shrink} (const double lambda=0.\+5) \begin{DoxyCompactList}\small\item\em Create \doxyref{Hard\+Shrink}{p.}{classmlpack_1_1ann_1_1HardShrink} object using specified hyperparameter lambda. \end{DoxyCompactList}\item {\footnotesize template$<$typename Data\+Type $>$ }\\void \textbf{ Backward} (const Data\+Type \&input, Data\+Type \&gy, Data\+Type \&g) \begin{DoxyCompactList}\small\item\em Ordinary feed backward pass of a neural network, calculating the function f(x) by propagating x backwards through f. \end{DoxyCompactList}\item Output\+Data\+Type const \& \textbf{ Delta} () const \begin{DoxyCompactList}\small\item\em Get the delta. \end{DoxyCompactList}\item Output\+Data\+Type \& \textbf{ Delta} () \begin{DoxyCompactList}\small\item\em Modify the delta. \end{DoxyCompactList}\item {\footnotesize template$<$typename Input\+Type , typename Output\+Type $>$ }\\void \textbf{ Forward} (const Input\+Type \&input, Output\+Type \&output) \begin{DoxyCompactList}\small\item\em Ordinary feed forward pass of a neural network, evaluating the function f(x) by propagating the activity forward through f. \end{DoxyCompactList}\item double const \& \textbf{ Lambda} () const \begin{DoxyCompactList}\small\item\em Get the hyperparameter lambda. \end{DoxyCompactList}\item double \& \textbf{ Lambda} () \begin{DoxyCompactList}\small\item\em Modify the hyperparameter lambda. \end{DoxyCompactList}\item Output\+Data\+Type const \& \textbf{ Output\+Parameter} () const \begin{DoxyCompactList}\small\item\em Get the output parameter. \end{DoxyCompactList}\item Output\+Data\+Type \& \textbf{ Output\+Parameter} () \begin{DoxyCompactList}\small\item\em Modify the output parameter. \end{DoxyCompactList}\item {\footnotesize template$<$typename Archive $>$ }\\void \textbf{ serialize} (Archive \&ar, const unsigned int) \begin{DoxyCompactList}\small\item\em Serialize the layer. \end{DoxyCompactList}\end{DoxyCompactItemize} \subsection{Detailed Description} \subsubsection*{template$<$typename Input\+Data\+Type = arma\+::mat, typename Output\+Data\+Type = arma\+::mat$>$\newline class mlpack\+::ann\+::\+Hard\+Shrink$<$ Input\+Data\+Type, Output\+Data\+Type $>$} Hard Shrink operator is defined as, \begin{eqnarray*} f(x) &=& \left\{ \begin{array}{lr} x & : x > lambda \\ x & : x < -lambda \\ 0 & : otherwise \end{array} \\ \right. f'(x) &=& \left\{ \begin{array}{lr} 1 & : x > lambda \\ 1 & : x < -lambda \\ 0 & : otherwise \end{array} \right. \end{eqnarray*} lambda is set to 0.\+5 by default. Definition at line 48 of file hardshrink.\+hpp. \subsection{Constructor \& Destructor Documentation} \mbox{\label{classmlpack_1_1ann_1_1HardShrink_a498f1df42a9d937e5025db81f6e63783}} \index{mlpack\+::ann\+::\+Hard\+Shrink@{mlpack\+::ann\+::\+Hard\+Shrink}!Hard\+Shrink@{Hard\+Shrink}} \index{Hard\+Shrink@{Hard\+Shrink}!mlpack\+::ann\+::\+Hard\+Shrink@{mlpack\+::ann\+::\+Hard\+Shrink}} \subsubsection{Hard\+Shrink()} {\footnotesize\ttfamily \textbf{ Hard\+Shrink} (\begin{DoxyParamCaption}\item[{const double}]{lambda = {\ttfamily 0.5} }\end{DoxyParamCaption})} Create \doxyref{Hard\+Shrink}{p.}{classmlpack_1_1ann_1_1HardShrink} object using specified hyperparameter lambda. \begin{DoxyParams}{Parameters} {\em lambda} & Is calculated by multiplying the noise level sigma of the input(noisy image) and a coefficient \textquotesingle{}a\textquotesingle{} which is one of the training parameters. Default value of lambda is 0.\+5. \\ \hline \end{DoxyParams} \subsection{Member Function Documentation} \mbox{\label{classmlpack_1_1ann_1_1HardShrink_a3ad74424be92ee20e633e1008e08004b}} \index{mlpack\+::ann\+::\+Hard\+Shrink@{mlpack\+::ann\+::\+Hard\+Shrink}!Backward@{Backward}} \index{Backward@{Backward}!mlpack\+::ann\+::\+Hard\+Shrink@{mlpack\+::ann\+::\+Hard\+Shrink}} \subsubsection{Backward()} {\footnotesize\ttfamily void Backward (\begin{DoxyParamCaption}\item[{const Data\+Type \&}]{input, }\item[{Data\+Type \&}]{gy, }\item[{Data\+Type \&}]{g }\end{DoxyParamCaption})} Ordinary feed backward pass of a neural network, calculating the function f(x) by propagating x backwards through f. Using the results from the feed forward pass. \begin{DoxyParams}{Parameters} {\em input} & The propagated input activation f(x). \\ \hline {\em gy} & The backpropagated error. \\ \hline {\em g} & The calculated gradient. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1HardShrink_a797f7edb44dd081e5e2b3cc316eef6bd}} \index{mlpack\+::ann\+::\+Hard\+Shrink@{mlpack\+::ann\+::\+Hard\+Shrink}!Delta@{Delta}} \index{Delta@{Delta}!mlpack\+::ann\+::\+Hard\+Shrink@{mlpack\+::ann\+::\+Hard\+Shrink}} \subsubsection{Delta()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily Output\+Data\+Type const\& Delta (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the delta. Definition at line 91 of file hardshrink.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1HardShrink_ad6601342d560219ce951d554e69e5e87}} \index{mlpack\+::ann\+::\+Hard\+Shrink@{mlpack\+::ann\+::\+Hard\+Shrink}!Delta@{Delta}} \index{Delta@{Delta}!mlpack\+::ann\+::\+Hard\+Shrink@{mlpack\+::ann\+::\+Hard\+Shrink}} \subsubsection{Delta()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily Output\+Data\+Type\& Delta (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the delta. Definition at line 93 of file hardshrink.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1HardShrink_a09440df0a90bdcc766e56e097d91205b}} \index{mlpack\+::ann\+::\+Hard\+Shrink@{mlpack\+::ann\+::\+Hard\+Shrink}!Forward@{Forward}} \index{Forward@{Forward}!mlpack\+::ann\+::\+Hard\+Shrink@{mlpack\+::ann\+::\+Hard\+Shrink}} \subsubsection{Forward()} {\footnotesize\ttfamily void Forward (\begin{DoxyParamCaption}\item[{const Input\+Type \&}]{input, }\item[{Output\+Type \&}]{output }\end{DoxyParamCaption})} Ordinary feed forward pass of a neural network, evaluating the function f(x) by propagating the activity forward through f. \begin{DoxyParams}{Parameters} {\em input} & Input data used for evaluating the Hard Shrink function. \\ \hline {\em output} & Resulting output activation. \\ \hline \end{DoxyParams} \mbox{\label{classmlpack_1_1ann_1_1HardShrink_acb669457ad59e62d0fccc5bae3a6c35e}} \index{mlpack\+::ann\+::\+Hard\+Shrink@{mlpack\+::ann\+::\+Hard\+Shrink}!Lambda@{Lambda}} \index{Lambda@{Lambda}!mlpack\+::ann\+::\+Hard\+Shrink@{mlpack\+::ann\+::\+Hard\+Shrink}} \subsubsection{Lambda()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily double const\& Lambda (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the hyperparameter lambda. Definition at line 96 of file hardshrink.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1HardShrink_aaf66629b989a326453647f42443c6a0c}} \index{mlpack\+::ann\+::\+Hard\+Shrink@{mlpack\+::ann\+::\+Hard\+Shrink}!Lambda@{Lambda}} \index{Lambda@{Lambda}!mlpack\+::ann\+::\+Hard\+Shrink@{mlpack\+::ann\+::\+Hard\+Shrink}} \subsubsection{Lambda()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily double\& Lambda (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the hyperparameter lambda. Definition at line 98 of file hardshrink.\+hpp. References Hard\+Shrink$<$ Input\+Data\+Type, Output\+Data\+Type $>$\+::serialize(). \mbox{\label{classmlpack_1_1ann_1_1HardShrink_a0ee21c2a36e5abad1e7a9d5dd00849f9}} \index{mlpack\+::ann\+::\+Hard\+Shrink@{mlpack\+::ann\+::\+Hard\+Shrink}!Output\+Parameter@{Output\+Parameter}} \index{Output\+Parameter@{Output\+Parameter}!mlpack\+::ann\+::\+Hard\+Shrink@{mlpack\+::ann\+::\+Hard\+Shrink}} \subsubsection{Output\+Parameter()\hspace{0.1cm}{\footnotesize\ttfamily [1/2]}} {\footnotesize\ttfamily Output\+Data\+Type const\& Output\+Parameter (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption}) const\hspace{0.3cm}{\ttfamily [inline]}} Get the output parameter. Definition at line 86 of file hardshrink.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1HardShrink_a21d5f745f02c709625a4ee0907f004a5}} \index{mlpack\+::ann\+::\+Hard\+Shrink@{mlpack\+::ann\+::\+Hard\+Shrink}!Output\+Parameter@{Output\+Parameter}} \index{Output\+Parameter@{Output\+Parameter}!mlpack\+::ann\+::\+Hard\+Shrink@{mlpack\+::ann\+::\+Hard\+Shrink}} \subsubsection{Output\+Parameter()\hspace{0.1cm}{\footnotesize\ttfamily [2/2]}} {\footnotesize\ttfamily Output\+Data\+Type\& Output\+Parameter (\begin{DoxyParamCaption}{ }\end{DoxyParamCaption})\hspace{0.3cm}{\ttfamily [inline]}} Modify the output parameter. Definition at line 88 of file hardshrink.\+hpp. \mbox{\label{classmlpack_1_1ann_1_1HardShrink_af0dd9205158ccf7bcfcd8ff81f79c927}} \index{mlpack\+::ann\+::\+Hard\+Shrink@{mlpack\+::ann\+::\+Hard\+Shrink}!serialize@{serialize}} \index{serialize@{serialize}!mlpack\+::ann\+::\+Hard\+Shrink@{mlpack\+::ann\+::\+Hard\+Shrink}} \subsubsection{serialize()} {\footnotesize\ttfamily void serialize (\begin{DoxyParamCaption}\item[{Archive \&}]{ar, }\item[{const unsigned}]{int }\end{DoxyParamCaption})} Serialize the layer. Referenced by Hard\+Shrink$<$ Input\+Data\+Type, Output\+Data\+Type $>$\+::\+Lambda(). The documentation for this class was generated from the following file\+:\begin{DoxyCompactItemize} \item /var/www/mlpack.\+ratml.\+org/mlpack.\+org/\+\_\+src/mlpack-\/3.\+3.\+0/src/mlpack/methods/ann/layer/\textbf{ hardshrink.\+hpp}\end{DoxyCompactItemize}